{"id":19287275,"url":"https://github.com/opendilab/di-engine","last_synced_at":"2025-05-12T15:28:58.760Z","repository":{"id":36980062,"uuid":"382787545","full_name":"opendilab/DI-engine","owner":"opendilab","description":"OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.","archived":false,"fork":false,"pushed_at":"2025-04-17T07:26:34.000Z","size":306391,"stargazers_count":3379,"open_issues_count":24,"forks_count":398,"subscribers_count":22,"default_branch":"main","last_synced_at":"2025-04-23T17:44:07.168Z","etag":null,"topics":["atari","distributed-reinforcement-learning","distributed-system","drl","exploration-exploitation","imitation-learning","impala","inverse-reinforcement-learning","minigrid","model-based-reinforcement-learning","mujoco","multiagent-reinforcement-learning","offline-rl","python","pytorch-rl","r2d2","reinforcement-learning","reinforcement-learning-algorithms","self-play","smac"],"latest_commit_sha":null,"homepage":"https://di-engine-docs.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/opendilab.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-07-04T07:11:05.000Z","updated_at":"2025-04-23T16:52:08.000Z","dependencies_parsed_at":"2023-09-22T13:26:59.775Z","dependency_job_id":"85ff0142-e776-42b0-8586-bfb13c174344","html_url":"https://github.com/opendilab/DI-engine","commit_stats":{"total_commits":758,"total_committers":55,"mean_commits":"13.781818181818181","dds":0.575197889182058,"last_synced_commit":"74c6a1e9230c19074dcd619ea4cafdcf2afb37ce"},"previous_names":[],"tags_count":22,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-engine","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-engine/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-engine/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-engine/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/opendilab","download_url":"https://codeload.github.com/opendilab/DI-engine/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253765390,"owners_count":21960723,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["atari","distributed-reinforcement-learning","distributed-system","drl","exploration-exploitation","imitation-learning","impala","inverse-reinforcement-learning","minigrid","model-based-reinforcement-learning","mujoco","multiagent-reinforcement-learning","offline-rl","python","pytorch-rl","r2d2","reinforcement-learning","reinforcement-learning-algorithms","self-play","smac"],"created_at":"2024-11-09T22:05:41.907Z","updated_at":"2025-05-12T15:28:58.711Z","avatar_url":"https://github.com/opendilab.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n \u003ca href=\"https://di-engine-docs.readthedocs.io/en/latest/\"\u003e\u003cimg width=\"1000px\" height=\"auto\" src=\"https://github.com/opendilab/DI-engine-docs/blob/main/source/images/head_image.png\"\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n---\n\n[![Twitter](https://img.shields.io/twitter/url?style=social\u0026url=https%3A%2F%2Ftwitter.com%2Fopendilab)](https://twitter.com/opendilab)\n[![PyPI](https://img.shields.io/pypi/v/DI-engine)](https://pypi.org/project/DI-engine/)\n![Conda](https://anaconda.org/opendilab/di-engine/badges/version.svg)\n![Conda update](https://anaconda.org/opendilab/di-engine/badges/latest_release_date.svg)\n![PyPI - Python Version](https://img.shields.io/pypi/pyversions/DI-engine)\n![PyTorch Version](https://img.shields.io/badge/dynamic/json?color=blue\u0026label=pytorch\u0026query=%24.pytorchVersion\u0026url=https%3A%2F%2Fgist.githubusercontent.com/PaParaZz1/54c5c44eeb94734e276b2ed5770eba8d/raw/85b94a54933a9369f8843cc2cea3546152a75661/badges.json)\n\n![Loc](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/HansBug/3690cccd811e4c5f771075c2f785c7bb/raw/loc.json)\n![Comments](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/HansBug/3690cccd811e4c5f771075c2f785c7bb/raw/comments.json)\n\n![Style](https://github.com/opendilab/DI-engine/actions/workflows/style.yml/badge.svg)\n[![Read en Docs](https://github.com/opendilab/DI-engine/actions/workflows/doc.yml/badge.svg)](https://di-engine-docs.readthedocs.io/en/latest)\n[![Read zh_CN Docs](https://img.shields.io/readthedocs/di-engine-docs?label=%E4%B8%AD%E6%96%87%E6%96%87%E6%A1%A3)](https://di-engine-docs.readthedocs.io/zh_CN/latest)\n![Unittest](https://github.com/opendilab/DI-engine/actions/workflows/unit_test.yml/badge.svg)\n![Algotest](https://github.com/opendilab/DI-engine/actions/workflows/algo_test.yml/badge.svg)\n![deploy](https://github.com/opendilab/DI-engine/actions/workflows/deploy.yml/badge.svg)\n[![codecov](https://codecov.io/gh/opendilab/DI-engine/branch/main/graph/badge.svg?token=B0Q15JI301)](https://codecov.io/gh/opendilab/DI-engine)\n\n![GitHub Org's stars](https://img.shields.io/github/stars/opendilab)\n[![GitHub stars](https://img.shields.io/github/stars/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/stargazers)\n[![GitHub forks](https://img.shields.io/github/forks/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/network)\n![GitHub commit activity](https://img.shields.io/github/commit-activity/m/opendilab/DI-engine)\n[![GitHub issues](https://img.shields.io/github/issues/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/issues)\n[![GitHub pulls](https://img.shields.io/github/issues-pr/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/pulls)\n[![Contributors](https://img.shields.io/github/contributors/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/graphs/contributors)\n[![GitHub license](https://img.shields.io/github/license/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/blob/master/LICENSE)\n[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow)](https://huggingface.co/OpenDILabCommunity)\n[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models?search=opendilab)\n[![discord badge](https://dcbadge.vercel.app/api/server/dkZS2JF56X?style=flat)](https://discord.gg/dkZS2JF56X)\n[![slack badge](https://img.shields.io/badge/Slack-join-blueviolet?logo=slack\u0026amp)](https://join.slack.com/t/opendilab/shared_invite/zt-v9tmv4fp-nUBAQEH1_Kuyu_q4plBssQ)\n\n\u003cdiv align=\"center\"\u003e\n \u003ca href=\"https://hellogithub.com/repository/175c1e13739c4e429d0abf2b32ec583d\" target=\"_blank\"\u003e\n \u003cimg src=\"https://api.hellogithub.com/v1/widgets/recommend.svg?rid=175c1e13739c4e429d0abf2b32ec583d\u0026claim_uid=cExIpHuMKdTQ6BW\" alt=\"Featured｜HelloGitHub\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" /\u003e\n \u003c/a\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\nUpdated on 2024.12.23 DI-engine-v0.5.3\n\n## Introduction to DI-engine\n\n[Documentation](https://di-engine-docs.readthedocs.io/en/latest/) | [中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/) | [Tutorials](https://di-engine-docs.readthedocs.io/en/latest/01_quickstart/index.html) | [Feature](#feature) | [Task \u0026 Middleware](https://di-engine-docs.readthedocs.io/en/latest/03_system/index.html) | [TreeTensor](#general-data-container-treetensor) | [Roadmap](https://github.com/opendilab/DI-engine/issues/548)\n\n**DI-engine** is a generalized decision intelligence engine for PyTorch and JAX.\n\nIt provides **python-first** and **asynchronous-native** task and middleware abstractions, and modularly integrates several of the most important decision-making concepts: Env, Policy and Model. Based on the above mechanisms, DI-engine supports **various [deep reinforcement learning](https://di-engine-docs.readthedocs.io/en/latest/10_concepts/index.html) algorithms** with superior performance, high efficiency, well-organized [documentation](https://di-engine-docs.readthedocs.io/en/latest/) and [unittest](https://github.com/opendilab/DI-engine/actions):\n\n- Most basic DRL algorithms: such as DQN, Rainbow, PPO, TD3, SAC, R2D2, IMPALA\n- Multi-agent RL algorithms: such as QMIX, WQMIX, MAPPO, HAPPO, ACE\n- Imitation learning algorithms (BC/IRL/GAIL): such as GAIL, SQIL, Guided Cost Learning, Implicit BC\n- Offline RL algorithms: BCQ, CQL, TD3BC, Decision Transformer, EDAC, Diffuser, Decision Diffuser, SO2\n- Model-based RL algorithms: SVG, STEVE, MBPO, DDPPO, DreamerV3\n- Exploration algorithms: HER, RND, ICM, NGU\n- LLM + RL Algorithms: PPO-max, DPO, PromptPG, PromptAWR\n- Other algorithms: such as PER, PLR, PCGrad\n- MCTS + RL algorithms: AlphaZero, MuZero, please refer to [LightZero](https://github.com/opendilab/LightZero)\n- Generative Model + RL algorithms: Diffusion-QL, QGPO, SRPO, please refer to [GenerativeRL](https://github.com/opendilab/GenerativeRL)\n\n\n**DI-engine** aims to **standardize different Decision Intelligence environments and applications**, supporting both academic research and prototype applications. Various training pipelines and customized decision AI applications are also supported:\n\n\u003cdetails open\u003e\n\u003csummary\u003e(Click to Collapse)\u003c/summary\u003e\n\n- Traditional academic environments\n - [DI-zoo](https://github.com/opendilab/DI-engine#environment-versatility): various decision intelligence demonstrations and benchmark environments with DI-engine.\n- Tutorial courses\n - [PPOxFamily](https://github.com/opendilab/PPOxFamily): PPO x Family DRL Tutorial Course\n- Real world decision AI applications\n - [DI-star](https://github.com/opendilab/DI-star): Decision AI in StarCraftII\n - [PsyDI](https://github.com/opendilab/PsyDI): Towards a Multi-Modal and Interactive Chatbot for Psychological Assessments\n - [DI-drive](https://github.com/opendilab/DI-drive): Auto-driving platform\n - [DI-sheep](https://github.com/opendilab/DI-sheep): Decision AI in 3 Tiles Game\n - [DI-smartcross](https://github.com/opendilab/DI-smartcross): Decision AI in Traffic Light Control\n - [DI-bioseq](https://github.com/opendilab/DI-bioseq): Decision AI in Biological Sequence Prediction and Searching\n - [DI-1024](https://github.com/opendilab/DI-1024): Deep Reinforcement Learning + 1024 Game\n- Research paper\n - [InterFuser](https://github.com/opendilab/InterFuser): [CoRL 2022] Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer\n - [ACE](https://github.com/opendilab/ACE): [AAAI 2023] ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency\n - [GoBigger](https://github.com/opendilab/GoBigger): [ICLR 2023] Multi-Agent Decision Intelligence Environment\n - [DOS](https://github.com/opendilab/DOS): [CVPR 2023] ReasonNet: End-to-End Driving with Temporal and Global Reasoning\n - [LightZero](https://github.com/opendilab/LightZero): [NeurIPS 2023 Spotlight] A lightweight and efficient MCTS/AlphaZero/MuZero algorithm toolkit\n - [SO2](https://github.com/opendilab/SO2): [AAAI 2024] A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning\n - [LMDrive](https://github.com/opendilab/LMDrive): [CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models\n - [SmartRefine](https://github.com/opendilab/SmartRefine): [CVPR 2024] SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction\n - [ReZero](https://github.com/opendilab/LightZero): Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze\n - [UniZero](https://github.com/opendilab/LightZero): Generalized and Efficient Planning with Scalable Latent World Models\n- Docs and Tutorials\n - [DI-engine-docs](https://github.com/opendilab/DI-engine-docs): Tutorials, best practice and the API reference.\n - [awesome-model-based-RL](https://github.com/opendilab/awesome-model-based-RL): A curated list of awesome Model-Based RL resources\n - [awesome-exploration-RL](https://github.com/opendilab/awesome-exploration-rl): A curated list of awesome exploration RL resources\n - [awesome-decision-transformer](https://github.com/opendilab/awesome-decision-transformer): A curated list of Decision Transformer resources\n - [awesome-RLHF](https://github.com/opendilab/awesome-RLHF): A curated list of reinforcement learning with human feedback resources\n - [awesome-multi-modal-reinforcement-learning](https://github.com/opendilab/awesome-multi-modal-reinforcement-learning): A curated list of Multi-Modal Reinforcement Learning resources\n - [awesome-diffusion-model-in-rl](https://github.com/opendilab/awesome-diffusion-model-in-rl): A curated list of Diffusion Model in RL resources\n - [awesome-ui-agents](https://github.com/opendilab/awesome-ui-agents): A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond\n - [awesome-AI-based-protein-design](https://github.com/opendilab/awesome-AI-based-protein-design): a collection of research papers for AI-based protein design\n - [awesome-end-to-end-autonomous-driving](https://github.com/opendilab/awesome-end-to-end-autonomous-driving): A curated list of awesome End-to-End Autonomous Driving resources\n - [awesome-driving-behavior-prediction](https://github.com/opendilab/awesome-driving-behavior-prediction): A collection of research papers for Driving Behavior Prediction\n\n \u003c/details\u003e\n\nOn the low-level end, DI-engine comes with a set of highly re-usable modules, including [RL optimization functions](https://github.com/opendilab/DI-engine/tree/main/ding/rl_utils), [PyTorch utilities](https://github.com/opendilab/DI-engine/tree/main/ding/torch_utils) and [auxiliary tools](https://github.com/opendilab/DI-engine/tree/main/ding/utils).\n\nBTW, **DI-engine** also has some special **system optimization and design** for efficient and robust large-scale RL training:\n\n\u003cdetails close\u003e\n\u003csummary\u003e(Click for Details)\u003c/summary\u003e\n\n- [treevalue](https://github.com/opendilab/treevalue): Tree-nested data structure\n- [DI-treetensor](https://github.com/opendilab/DI-treetensor): Tree-nested PyTorch tensor Lib\n- [DI-toolkit](https://github.com/opendilab/DI-toolkit): A simple toolkit package for decision intelligence\n- [DI-orchestrator](https://github.com/opendilab/DI-orchestrator): RL Kubernetes Custom Resource and Operator Lib\n- [DI-hpc](https://github.com/opendilab/DI-hpc): RL HPC OP Lib\n- [DI-store](https://github.com/opendilab/DI-store): RL Object Store\n\n\u003c/details\u003e\n\nHave fun with exploration and exploitation.\n\n## Outline\n\n- [Introduction to DI-engine](#introduction-to-di-engine)\n- [Outline](#outline)\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Feature](#feature)\n - [Algorithm Versatility](#algorithm-versatility)\n - [Environment Versatility](#environment-versatility)\n - [General Data Container: TreeTensor](#general-data-container-treetensor)\n- [Feedback and Contribution](#feedback-and-contribution)\n- [Supporters](#supporters)\n - [↳ Stargazers](#-stargazers)\n - [↳ Forkers](#-forkers)\n- [Citation](#citation)\n- [License](#license)\n\n## Installation\n\nYou can simply install DI-engine from PyPI with the following command:\n\n```bash\npip install DI-engine\n```\n\nFor more information about installation, you can refer to [installation](https://di-engine-docs.readthedocs.io/en/latest/01_quickstart/installation.html).\n\nAnd our dockerhub repo can be found [here](https://hub.docker.com/repository/docker/opendilab/ding)，we prepare `base image` and `env image` with common RL environments.\n\n\u003cdetails close\u003e\n\u003csummary\u003e(Click for Details)\u003c/summary\u003e\n\n- base: opendilab/ding:nightly\n- rpc: opendilab/ding:nightly-rpc\n- atari: opendilab/ding:nightly-atari\n- mujoco: opendilab/ding:nightly-mujoco\n- dmc: opendilab/ding:nightly-dmc2gym\n- metaworld: opendilab/ding:nightly-metaworld\n- smac: opendilab/ding:nightly-smac\n- grf: opendilab/ding:nightly-grf\n- cityflow: opendilab/ding:nightly-cityflow\n- evogym: opendilab/ding:nightly-evogym\n- d4rl: opendilab/ding:nightly-d4rl\n\n\u003c/details\u003e\n\nThe detailed documentation are hosted on [doc](https://di-engine-docs.readthedocs.io/en/latest/) | [中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/).\n\n## Quick Start\n\n[3 Minutes Kickoff](https://di-engine-docs.readthedocs.io/en/latest/01_quickstart/first_rl_program.html)\n\n[3 Minutes Kickoff (colab)](https://colab.research.google.com/drive/1_7L-QFDfeCvMvLJzRyBRUW5_Q6ESXcZ4)\n\n[DI-engine Huggingface Kickoff (colab)](https://colab.research.google.com/drive/1UH1GQOjcHrmNSaW77hnLGxFJrLSLwCOk)\n\n[How to migrate a new **RL Env**](https://di-engine-docs.readthedocs.io/en/latest/11_dizoo/index.html) | [如何迁移一个新的**强化学习环境**](https://di-engine-docs.readthedocs.io/zh_CN/latest/11_dizoo/index_zh.html)\n\n[How to customize the neural network model](https://di-engine-docs.readthedocs.io/en/latest/04_best_practice/custom_model.html) | [如何定制策略使用的**神经网络模型**](https://di-engine-docs.readthedocs.io/zh_CN/latest/04_best_practice/custom_model_zh.html)\n\n[测试/部署 **强化学习策略** 的样例](https://github.com/opendilab/DI-engine/blob/main/dizoo/classic_control/cartpole/entry/cartpole_c51_deploy.py)\n\n[新老 pipeline 的异同对比](https://di-engine-docs.readthedocs.io/zh_CN/latest/04_best_practice/diff_in_new_pipeline_zh.html)\n\n## Feature\n\n### Algorithm Versatility\n\n\u003cdetails open\u003e\n\u003csummary\u003e(Click to Collapse)\u003c/summary\u003e\n\n![discrete](https://img.shields.io/badge/-discrete-brightgreen) \u0026nbsp;discrete means discrete action space, which is only label in normal DRL algorithms (1-23)\n\n![continuous](https://img.shields.io/badge/-continous-green) \u0026nbsp;means continuous action space, which is only label in normal DRL algorithms (1-23)\n\n![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) \u0026nbsp;means hybrid (discrete + continuous) action space (1-23)\n\n![dist](https://img.shields.io/badge/-distributed-blue) \u0026nbsp;[Distributed Reinforcement Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/distributed_rl.html)｜[分布式强化学习](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/distributed_rl_zh.html)\n\n![MARL](https://img.shields.io/badge/-MARL-yellow) \u0026nbsp;[Multi-Agent Reinforcement Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/multi_agent_cooperation_rl.html)｜[多智能体强化学习](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/multi_agent_cooperation_rl_zh.html)\n\n![exp](https://img.shields.io/badge/-exploration-orange) \u0026nbsp;[Exploration Mechanisms in Reinforcement Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/exploration_rl.html)｜[强化学习中的探索机制](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/exploration_rl_zh.html)\n\n![IL](https://img.shields.io/badge/-IL-purple) \u0026nbsp;[Imitation Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/imitation_learning.html)｜[模仿学习](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/imitation_learning_zh.html)\n\n![offline](https://img.shields.io/badge/-offlineRL-darkblue) \u0026nbsp;[Offiline Reinforcement Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/offline_rl.html)｜[离线强化学习](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/offline_rl_zh.html)\n\n![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) \u0026nbsp;[Model-Based Reinforcement Learning](https://di-engine-docs.readthedocs.io/en/latest/02_algo/model_based_rl.html)｜[基于模型的强化学习](https://di-engine-docs.readthedocs.io/zh_CN/latest/02_algo/model_based_rl_zh.html)\n\n![other](https://img.shields.io/badge/-other-lightgrey) \u0026nbsp;means other sub-direction algorithms, usually as plugin-in in the whole pipeline\n\nP.S: The `.py` file in `Runnable Demo` can be found in `dizoo`\n\n\n| No. | Algorithm | Label | Doc and Implementation | Runnable Demo |\n| :-: | :---------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------: |\n| 1 | [DQN](https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [DQN doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/dqn.html)\u003cbr\u003e[DQN中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/dqn_zh.html)\u003cbr\u003e[policy/dqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/dqn.py) | python3 -u cartpole_dqn_main.py / ding -m serial -c cartpole_dqn_config.py -s 0 |\n| 2 | [C51](https://arxiv.org/pdf/1707.06887.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [C51 doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/c51.html)\u003cbr\u003e[policy/c51](https://github.com/opendilab/DI-engine/blob/main/ding/policy/c51.py) | ding -m serial -c cartpole_c51_config.py -s 0 |\n| 3 | [QRDQN](https://arxiv.org/pdf/1710.10044.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [QRDQN doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/qrdqn.html)\u003cbr\u003e[policy/qrdqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/qrdqn.py) | ding -m serial -c cartpole_qrdqn_config.py -s 0 |\n| 4 | [IQN](https://arxiv.org/pdf/1806.06923.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [IQN doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/iqn.html)\u003cbr\u003e[policy/iqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/iqn.py) | ding -m serial -c cartpole_iqn_config.py -s 0 |\n| 5 | [FQF](https://arxiv.org/pdf/1911.02140.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [FQF doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/fqf.html)\u003cbr\u003e[policy/fqf](https://github.com/opendilab/DI-engine/blob/main/ding/policy/fqf.py) | ding -m serial -c cartpole_fqf_config.py -s 0 |\n| 6 | [Rainbow](https://arxiv.org/pdf/1710.02298.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [Rainbow doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/rainbow.html)\u003cbr\u003e[policy/rainbow](https://github.com/opendilab/DI-engine/blob/main/ding/policy/rainbow.py) | ding -m serial -c cartpole_rainbow_config.py -s 0 |\n| 7 | [SQL](https://arxiv.org/pdf/1702.08165.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![continuous](https://img.shields.io/badge/-continous-green) | [SQL doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/sql.html)\u003cbr\u003e[policy/sql](https://github.com/opendilab/DI-engine/blob/main/ding/policy/sql.py) | ding -m serial -c cartpole_sql_config.py -s 0 |\n| 8 | [R2D2](https://openreview.net/forum?id=r1lyTjAqYX) | ![dist](https://img.shields.io/badge/-distributed-blue)![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [R2D2 doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/r2d2.html)\u003cbr\u003e[policy/r2d2](https://github.com/opendilab/DI-engine/blob/main/ding/policy/r2d2.py) | ding -m serial -c cartpole_r2d2_config.py -s 0 |\n| 9 | [PG](https://proceedings.neurips.cc/paper/1999/file/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [PG doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/a2c.html)\u003cbr\u003e[policy/pg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/pg.py) | ding -m serial -c cartpole_pg_config.py -s 0 |\n| 10 | [PromptPG](https://arxiv.org/abs/2209.14610) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [policy/prompt_pg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/prompt_pg.py) | ding -m serial_onpolicy -c tabmwp_pg_config.py -s 0 |\n| 11 | [A2C](https://arxiv.org/pdf/1602.01783.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [A2C doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/a2c.html)\u003cbr\u003e[policy/a2c](https://github.com/opendilab/DI-engine/blob/main/ding/policy/a2c.py) | ding -m serial -c cartpole_a2c_config.py -s 0 |\n| 12 | [PPO](https://arxiv.org/abs/1707.06347)/[MAPPO](https://arxiv.org/pdf/2103.01955.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![continuous](https://img.shields.io/badge/-continous-green)![MARL](https://img.shields.io/badge/-MARL-yellow) | [PPO doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html)\u003cbr\u003e[policy/ppo](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ppo.py) | python3 -u cartpole_ppo_main.py / ding -m serial_onpolicy -c cartpole_ppo_config.py -s 0 |\n| 13 | [PPG](https://arxiv.org/pdf/2009.04416.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [PPG doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppg.html)\u003cbr\u003e[policy/ppg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ppg.py) | python3 -u cartpole_ppg_main.py |\n| 14 | [ACER](https://arxiv.org/pdf/1611.01224.pdf) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![continuous](https://img.shields.io/badge/-continous-green) | [ACER doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/acer.html)\u003cbr\u003e[policy/acer](https://github.com/opendilab/DI-engine/blob/main/ding/policy/acer.py) | ding -m serial -c cartpole_acer_config.py -s 0 |\n| 15 | [IMPALA](https://arxiv.org/abs/1802.01561) | ![dist](https://img.shields.io/badge/-distributed-blue)![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [IMPALA doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/impala.html)\u003cbr\u003e[policy/impala](https://github.com/opendilab/DI-engine/blob/main/ding/policy/impala.py) | ding -m serial -c cartpole_impala_config.py -s 0 |\n| 16 | [DDPG](https://arxiv.org/pdf/1509.02971.pdf)/[PADDPG](https://arxiv.org/pdf/1511.04143.pdf) | ![continuous](https://img.shields.io/badge/-continous-green)![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [DDPG doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ddpg.html)\u003cbr\u003e[policy/ddpg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ddpg.py) | ding -m serial -c pendulum_ddpg_config.py -s 0 |\n| 17 | [TD3](https://arxiv.org/pdf/1802.09477.pdf) | ![continuous](https://img.shields.io/badge/-continous-green)![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [TD3 doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3.html)\u003cbr\u003e[policy/td3](https://github.com/opendilab/DI-engine/blob/main/ding/policy/td3.py) | python3 -u pendulum_td3_main.py / ding -m serial -c pendulum_td3_config.py -s 0 |\n| 18 | [D4PG](https://arxiv.org/pdf/1804.08617.pdf) | ![continuous](https://img.shields.io/badge/-continous-green) | [D4PG doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/d4pg.html)\u003cbr\u003e[policy/d4pg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/d4pg.py) | python3 -u pendulum_d4pg_config.py |\n| 19 | [SAC](https://arxiv.org/abs/1801.01290)/[MASAC] | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![continuous](https://img.shields.io/badge/-continous-green)![MARL](https://img.shields.io/badge/-MARL-yellow) | [SAC doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html)\u003cbr\u003e[policy/sac](https://github.com/opendilab/DI-engine/blob/main/ding/policy/sac.py) | ding -m serial -c pendulum_sac_config.py -s 0 |\n| 20 | [PDQN](https://arxiv.org/pdf/1810.06394.pdf) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [policy/pdqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/pdqn.py) | ding -m serial -c gym_hybrid_pdqn_config.py -s 0 |\n| 21 | [MPDQN](https://arxiv.org/pdf/1905.04388.pdf) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [policy/pdqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/pdqn.py) | ding -m serial -c gym_hybrid_mpdqn_config.py -s 0 |\n| 22 | [HPPO](https://arxiv.org/pdf/1903.01344.pdf) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [policy/ppo](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ppo.py) | ding -m serial_onpolicy -c gym_hybrid_hppo_config.py -s 0 |\n| 23 | [BDQ](https://arxiv.org/pdf/1711.08946.pdf) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | [policy/bdq](https://github.com/opendilab/DI-engine/blob/main/ding/policy/dqn.py) | python3 -u hopper_bdq_config.py |\n| 24 | [MDQN](https://arxiv.org/abs/2007.14430) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [policy/mdqn](https://github.com/opendilab/DI-engine/blob/main/ding/policy/mdqn.py) | python3 -u asterix_mdqn_config.py |\n| 25 | [QMIX](https://arxiv.org/pdf/1803.11485.pdf) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [QMIX doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/qmix.html)\u003cbr\u003e[policy/qmix](https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py) | ding -m serial -c smac_3s5z_qmix_config.py -s 0 |\n| 26 | [COMA](https://arxiv.org/pdf/1705.08926.pdf) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [COMA doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/coma.html)\u003cbr\u003e[policy/coma](https://github.com/opendilab/DI-engine/blob/main/ding/policy/coma.py) | ding -m serial -c smac_3s5z_coma_config.py -s 0 |\n| 27 | [QTran](https://arxiv.org/abs/1905.05408) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [policy/qtran](https://github.com/opendilab/DI-engine/blob/main/ding/policy/qtran.py) | ding -m serial -c smac_3s5z_qtran_config.py -s 0 |\n| 28 | [WQMIX](https://arxiv.org/abs/2006.10800) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [WQMIX doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/wqmix.html)\u003cbr\u003e[policy/wqmix](https://github.com/opendilab/DI-engine/blob/main/ding/policy/wqmix.py) | ding -m serial -c smac_3s5z_wqmix_config.py -s 0 |\n| 29 | [CollaQ](https://arxiv.org/pdf/2010.08531.pdf) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [CollaQ doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/collaq.html)\u003cbr\u003e[policy/collaq](https://github.com/opendilab/DI-engine/blob/main/ding/policy/collaq.py) | ding -m serial -c smac_3s5z_collaq_config.py -s 0 |\n| 30 | [MADDPG](https://arxiv.org/pdf/1706.02275.pdf) | ![MARL](https://img.shields.io/badge/-MARL-yellow) | [MADDPG doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ddpg.html)\u003cbr\u003e[policy/ddpg](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ddpg.py) | ding -m serial -c ptz_simple_spread_maddpg_config.py -s 0 |\n| 31 | [GAIL](https://arxiv.org/pdf/1606.03476.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [GAIL doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/gail.html)\u003cbr\u003e[reward_model/gail](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/gail_irl_model.py) | ding -m serial_gail -c cartpole_dqn_gail_config.py -s 0 |\n| 32 | [SQIL](https://arxiv.org/pdf/1905.11108.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [SQIL doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/sqil.html)\u003cbr\u003e[entry/sqil](https://github.com/opendilab/DI-engine/blob/main/ding/entry/serial_entry_sqil.py) | ding -m serial_sqil -c cartpole_sqil_config.py -s 0 |\n| 33 | [DQFD](https://arxiv.org/pdf/1704.03732.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [DQFD doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/dqfd.html)\u003cbr\u003e[policy/dqfd](https://github.com/opendilab/DI-engine/blob/main/ding/policy/dqfd.py) | ding -m serial_dqfd -c cartpole_dqfd_config.py -s 0 |\n| 34 | [R2D3](https://arxiv.org/pdf/1909.01387.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [R2D3 doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/r2d3.html)\u003cbr\u003e[R2D3中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/r2d3_zh.html)\u003cbr\u003e[policy/r2d3](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/r2d3_zh.html) | python3 -u pong_r2d3_r2d2expert_config.py |\n| 35 | [Guided Cost Learning](https://arxiv.org/pdf/1603.00448.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [Guided Cost Learning中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/guided_cost_zh.html)\u003cbr\u003e[reward_model/guided_cost](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/guided_cost_reward_model.py) | python3 lunarlander_gcl_config.py |\n| 36 | [TREX](https://arxiv.org/abs/1904.06387) | ![IL](https://img.shields.io/badge/-IL-purple) | [TREX doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/trex.html)\u003cbr\u003e[reward_model/trex](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/trex_reward_model.py) | python3 mujoco_trex_main.py |\n| 37 | [Implicit Behavorial Cloning](https://implicitbc.github.io/) (DFO+MCMC) | ![IL](https://img.shields.io/badge/-IL-purple) | [policy/ibc](https://github.com/opendilab/DI-engine/blob/main/ding/policy/ibc.py) \u003cbr\u003e [model/template/ebm](https://github.com/opendilab/DI-engine/blob/main/ding/model/template/ebm.py) | python3 d4rl_ibc_main.py -s 0 -c pen_human_ibc_mcmc_config.py |\n| 38 | [BCO](https://arxiv.org/pdf/1805.01954.pdf) | ![IL](https://img.shields.io/badge/-IL-purple) | [entry/bco](https://github.com/opendilab/DI-engine/blob/main/ding/entry/serial_entry_bco.py) | python3 -u cartpole_bco_config.py |\n| 39 | [HER](https://arxiv.org/pdf/1707.01495.pdf) | ![exp](https://img.shields.io/badge/-exploration-orange) | [HER doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/her.html)\u003cbr\u003e[reward_model/her](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/her_reward_model.py) | python3 -u bitflip_her_dqn.py |\n| 40 | [RND](https://arxiv.org/abs/1810.12894) | ![exp](https://img.shields.io/badge/-exploration-orange) | [RND doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/rnd.html)\u003cbr\u003e[reward_model/rnd](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py) | python3 -u cartpole_rnd_onppo_config.py |\n| 41 | [ICM](https://arxiv.org/pdf/1705.05363.pdf) | ![exp](https://img.shields.io/badge/-exploration-orange) | [ICM doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/icm.html)\u003cbr\u003e[ICM中文文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/12_policies/icm_zh.html)\u003cbr\u003e[reward_model/icm](https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/icm_reward_model.py) | python3 -u cartpole_ppo_icm_config.py |\n| 42 | [CQL](https://arxiv.org/pdf/2006.04779.pdf) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | [CQL doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/cql.html)\u003cbr\u003e[policy/cql](https://github.com/opendilab/DI-engine/blob/main/ding/policy/cql.py) | python3 -u d4rl_cql_main.py |\n| 43 | [TD3BC](https://arxiv.org/pdf/2106.06860.pdf) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | [TD3BC doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3_bc.html)\u003cbr\u003e[policy/td3_bc](https://github.com/opendilab/DI-engine/blob/main/ding/policy/td3_bc.py) | python3 -u d4rl_td3_bc_main.py |\n| 44 | [Decision Transformer](https://arxiv.org/pdf/2106.01345.pdf) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | [policy/dt](https://github.com/opendilab/DI-engine/blob/main/ding/policy/dt.py) | python3 -u d4rl_dt_mujoco.py |\n| 45 | [EDAC](https://arxiv.org/pdf/2110.01548.pdf) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | [EDAC doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/edac.html)\u003cbr\u003e[policy/edac](https://github.com/opendilab/DI-engine/blob/main/ding/policy/edac.py) | python3 -u d4rl_edac_main.py |\n| 46 | [QGPO](https://arxiv.org/pdf/2304.12824.pdf) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | [QGPO doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/qgpo.html)\u003cbr\u003e[policy/qgpo](https://github.com/opendilab/DI-engine/blob/main/ding/policy/qgpo.py) | python3 -u ding/example/qgpo.py |\n| 47 | MBSAC([SAC](https://arxiv.org/abs/1801.01290)+[MVE](https://arxiv.org/abs/1803.00101)+[SVG](https://arxiv.org/abs/1510.09142)) | ![continuous](https://img.shields.io/badge/-continous-green)![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) | [policy/mbpolicy/mbsac](https://github.com/opendilab/DI-engine/blob/main/ding/policy/mbpolicy/mbsac.py) | python3 -u pendulum_mbsac_mbpo_config.py \\ python3 -u pendulum_mbsac_ddppo_config.py |\n| 48 | STEVESAC([SAC](https://arxiv.org/abs/1801.01290)+[STEVE](https://arxiv.org/abs/1807.01675)+[SVG](https://arxiv.org/abs/1510.09142)) | ![continuous](https://img.shields.io/badge/-continous-green)![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) | [policy/mbpolicy/mbsac](https://github.com/opendilab/DI-engine/blob/main/ding/policy/mbpolicy/mbsac.py) | python3 -u pendulum_stevesac_mbpo_config.py |\n| 49 | [MBPO](https://arxiv.org/pdf/1906.08253.pdf) | ![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) | [MBPO doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/mbpo.html)\u003cbr\u003e[world_model/mbpo](https://github.com/opendilab/DI-engine/blob/main/ding/world_model/mbpo.py) | python3 -u pendulum_sac_mbpo_config.py |\n| 50 | [DDPPO](https://openreview.net/forum?id=rzvOQrnclO0) | ![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) | [world_model/ddppo](https://github.com/opendilab/DI-engine/blob/main/ding/world_model/ddppo.py) | python3 -u pendulum_mbsac_ddppo_config.py |\n| 51 | [DreamerV3](https://arxiv.org/pdf/2301.04104.pdf) | ![mbrl](https://img.shields.io/badge/-ModelBasedRL-lightblue) | [world_model/dreamerv3](https://github.com/opendilab/DI-engine/blob/main/ding/world_model/dreamerv3.py) | python3 -u cartpole_balance_dreamer_config.py |\n| 52 | [PER](https://arxiv.org/pdf/1511.05952.pdf) | ![other](https://img.shields.io/badge/-other-lightgrey) | [worker/replay_buffer](https://github.com/opendilab/DI-engine/blob/main/ding/worker/replay_buffer/advanced_buffer.py) | `rainbow demo` |\n| 53 | [GAE](https://arxiv.org/pdf/1506.02438.pdf) | ![other](https://img.shields.io/badge/-other-lightgrey) | [rl_utils/gae](https://github.com/opendilab/DI-engine/blob/main/ding/rl_utils/gae.py) | `ppo demo` |\n| 54 | [ST-DIM](https://arxiv.org/pdf/1906.08226.pdf) | ![other](https://img.shields.io/badge/-other-lightgrey) | [torch_utils/loss/contrastive_loss](https://github.com/opendilab/DI-engine/blob/main/ding/torch_utils/loss/contrastive_loss.py) | ding -m serial -c cartpole_dqn_stdim_config.py -s 0 |\n| 55 | [PLR](https://arxiv.org/pdf/2010.03934.pdf) | ![other](https://img.shields.io/badge/-other-lightgrey) | [PLR doc](https://di-engine-docs.readthedocs.io/en/latest/12_policies/plr.html)\u003cbr\u003e[data/level_replay/level_sampler](https://github.com/opendilab/DI-engine/blob/main/ding/data/level_replay/level_sampler.py) | python3 -u bigfish_plr_config.py -s 0 |\n| 56 | [PCGrad](https://arxiv.org/pdf/2001.06782.pdf) | ![other](https://img.shields.io/badge/-other-lightgrey) | [torch_utils/optimizer_helper/PCGrad](https://github.com/opendilab/DI-engine/blob/main/ding/data/torch_utils/optimizer_helper.py) | python3 -u multi_mnist_pcgrad_main.py -s 0 |\n| 57 | [AWR](https://arxiv.org/pdf/1910.00177) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | [policy/ibc](https://github.com/opendilab/DI-engine/blob/main/ding/policy/prompt_awr.py) | python3 -u tabmwp_awr_config.py |\n\n\u003c/details\u003e\n\n### Environment Versatility\n\n\u003cdetails open\u003e\n\u003csummary\u003e(Click to Collapse)\u003c/summary\u003e\n\n| No | Environment | Label | Visualization | Code and Doc Links |\n| :-: | :--------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |\n| 1 | [Atari](https://ale.farama.org) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/atari/atari.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/atari/envs) \u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/atari_zh.html) |\n| 2 | [box2d/bipedalwalker](https://github.com/openai/gym/tree/master/gym/envs/box2d) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/box2d/bipedalwalker/original.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/box2d/bipedalwalker/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/bipedalwalker.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/bipedalwalker_zh.html) |\n| 3 | [box2d/lunarlander](https://github.com/openai/gym/tree/master/gym/envs/box2d) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/box2d/lunarlander/lunarlander.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/box2d/lunarlander/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/lunarlander_zh.html) |\n| 4 | [classic_control/cartpole](https://github.com/openai/gym/tree/master/gym/envs/classic_control) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/classic_control/cartpole/cartpole.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/classic_control/cartpole/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/cartpole.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/cartpole_zh.html) |\n| 5 | [classic_control/pendulum](https://github.com/openai/gym/tree/master/gym/envs/classic_control) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/classic_control/pendulum/pendulum.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/classic_control/pendulum/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/pendulum.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/pendulum_zh.html) |\n| 6 | [competitive_rl](https://github.com/cuhkrlcourse/competitive-rl) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![selfplay](https://img.shields.io/badge/-selfplay-blue) | ![original](./dizoo/competitive_rl/competitive_rl.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo.classic_control)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/en/latest/13_envs/competitive_rl_zh.html) |\n| 7 | [gfootball](https://github.com/google-research/football) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![sparse](https://img.shields.io/badge/-sparse%20reward-orange)![selfplay](https://img.shields.io/badge/-selfplay-blue) | ![original](./dizoo/gfootball/gfootball.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo.gfootball/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/gfootball.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/en/latest/13_envs/gfootball_zh.html) |\n| 8 | [minigrid](https://github.com/maximecb/gym-minigrid) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![sparse](https://img.shields.io/badge/-sparse%20reward-orange) | ![original](./dizoo/minigrid/minigrid.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/minigrid/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/minigrid.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/en/latest/13_envs/minigrid_zh.html) |\n| 9 | [MuJoCo](https://github.com/openai/gym/tree/master/gym/envs/mujoco) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/mujoco/mujoco.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/majoco/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco_zh.html) |\n| 10 | [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![continuous](https://img.shields.io/badge/-continous-green) ![marl](https://img.shields.io/badge/-MARL-yellow) | ![original](./dizoo/petting_zoo/petting_zoo_mpe_simple_spread.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/petting_zoo/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/pettingzoo.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/pettingzoo_zh.html) |\n| 11 | [overcooked](https://github.com/HumanCompatibleAI/overcooked-demo) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![marl](https://img.shields.io/badge/-MARL-yellow) | ![original](./dizoo/overcooked/overcooked.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/overcooded/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/overcooked.html) |\n| 12 | [procgen](https://github.com/openai/procgen) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/procgen/coinrun.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/procgen)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/procgen.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/procgen_zh.html) |\n| 13 | [pybullet](https://github.com/benelot/pybullet-gym) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/pybullet/pybullet.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/pybullet/envs)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/pybullet_zh.html) |\n| 14 | [smac](https://github.com/oxwhirl/smac) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![marl](https://img.shields.io/badge/-MARL-yellow)![selfplay](https://img.shields.io/badge/-selfplay-blue)![sparse](https://img.shields.io/badge/-sparse%20reward-orange) | ![original](./dizoo/smac/smac.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/smac/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/smac.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/smac_zh.html) |\n| 15 | [d4rl](https://github.com/rail-berkeley/d4rl) | ![offline](https://img.shields.io/badge/-offlineRL-darkblue) | ![ori](dizoo/d4rl/d4rl.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/d4rl)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/d4rl_zh.html) |\n| 16 | league_demo | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![selfplay](https://img.shields.io/badge/-selfplay-blue) | ![original](./dizoo/league_demo/league_demo.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/league_demo/envs) |\n| 17 | pomdp atari | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/pomdp/envs) |\n| 18 | [bsuite](https://github.com/deepmind/bsuite) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/bsuite/bsuite.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/bsuite/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs//bsuite.html) \u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/bsuite_zh.html) |\n| 19 | [ImageNet](https://www.image-net.org/) | ![IL](https://img.shields.io/badge/-IL/SL-purple) | ![original](./dizoo/image_classification/imagenet.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/image_classification)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/image_cls_zh.html) |\n| 20 | [slime_volleyball](https://github.com/hardmaru/slimevolleygym) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen)![selfplay](https://img.shields.io/badge/-selfplay-blue) | ![ori](dizoo/slime_volley/slime_volley.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/slime_volley)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/slime_volleyball.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/slime_volleyball_zh.html) |\n| 21 | [gym_hybrid](https://github.com/thomashirtz/gym-hybrid) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | ![ori](dizoo/gym_hybrid/moving_v0.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_hybrid)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/gym_hybrid.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/gym_hybrid_zh.html) |\n| 22 | [GoBigger](https://github.com/opendilab/GoBigger) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen)![marl](https://img.shields.io/badge/-MARL-yellow)![selfplay](https://img.shields.io/badge/-selfplay-blue) | ![ori](./dizoo/gobigger_overview.gif) | [dizoo link](https://github.com/opendilab/GoBigger-Challenge-2021/tree/main/di_baseline)\u003cbr\u003e[env tutorial](https://gobigger.readthedocs.io/en/latest/index.html)\u003cbr\u003e[环境指南](https://gobigger.readthedocs.io/zh_CN/latest/) |\n| 23 | [gym_soccer](https://github.com/openai/gym-soccer) | ![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) | ![ori](dizoo/gym_soccer/half_offensive.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_soccer)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/gym_soccer_zh.html) |\n| 24 | [multiagent_mujoco](https://github.com/schroederdewitt/multiagent_mujoco) | ![continuous](https://img.shields.io/badge/-continous-green) ![marl](https://img.shields.io/badge/-MARL-yellow) | ![original](./dizoo/mujoco/mujoco.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/multiagent_mujoco/envs)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/mujoco_zh.html) |\n| 25 | bitflip | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![sparse](https://img.shields.io/badge/-sparse%20reward-orange) | ![original](./dizoo/bitflip/bitflip.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/bitflip/envs)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/bitflip_zh.html) |\n| 26 | [sokoban](https://github.com/mpSchrader/gym-sokoban) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![Game 2](https://github.com/mpSchrader/gym-sokoban/raw/default/docs/Animations/solved_4.gif?raw=true) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/sokoban/envs)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/sokoban.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/sokoban_zh.html) |\n| 27 | [gym_anytrading](https://github.com/AminHP/gym-anytrading) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/gym_anytrading/envs/position.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_anytrading) \u003cbr\u003e [env tutorial](https://github.com/opendilab/DI-engine/blob/main/dizoo/gym_anytrading/envs/README.md) |\n| 28 | [mario](https://github.com/Kautenja/gym-super-mario-bros) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/mario/mario.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/mario) \u003cbr\u003e [env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/gym_super_mario_bros.html) \u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/gym_super_mario_bros_zh.html) |\n| 29 | [dmc2gym](https://github.com/denisyarats/dmc2gym) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/dmc2gym/dmc2gym_cheetah.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/dmc2gym)\u003cbr\u003e[env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/dmc2gym.html)\u003cbr\u003e[环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/dmc2gym_zh.html) |\n| 30 | [evogym](https://github.com/EvolutionGym/evogym) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/evogym/evogym.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/evogym/envs) \u003cbr\u003e [env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/evogym.html) \u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/Evogym_zh.html) |\n| 31 | [gym-pybullet-drones](https://github.com/utiasDSL/gym-pybullet-drones) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/gym_pybullet_drones/gym_pybullet_drones.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_pybullet_drones/envs)\u003cbr\u003e环境指南 |\n| 32 | [beergame](https://github.com/OptMLGroup/DeepBeerInventory-RL) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/beergame/beergame.png) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/beergame/envs)\u003cbr\u003e环境指南 |\n| 33 | [classic_control/acrobot](https://github.com/openai/gym/tree/master/gym/envs/classic_control) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/classic_control/acrobot/acrobot.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/classic_control/acrobot/envs)\u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/acrobot_zh.html) |\n| 34 | [box2d/car_racing](https://github.com/openai/gym/blob/master/gym/envs/box2d/car_racing.py) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) \u003cbr\u003e ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/box2d/carracing/car_racing.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/box2d/carracing/envs)\u003cbr\u003e环境指南 |\n| 35 | [metadrive](https://github.com/metadriverse/metadrive) | ![continuous](https://img.shields.io/badge/-continous-green) | ![original](./dizoo/metadrive/metadrive_env.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/metadrive/env)\u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/metadrive_zh.html) |\n| 36 | [cliffwalking](https://github.com/openai/gym/blob/master/gym/envs/toy_text/cliffwalking.py) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/cliffwalking/cliff_walking.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/cliffwalking/envs)\u003cbr\u003e env tutorial \u003cbr\u003e 环境指南 |\n| 37 | [tabmwp](https://promptpg.github.io/explore.html) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/tabmwp/tabmwp.jpeg) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/tabmwp) \u003cbr\u003e env tutorial \u003cbr\u003e 环境指南 |\n| 38 | [frozen_lake](https://gymnasium.farama.org/environments/toy_text/frozen_lake) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/frozen_lake/FrozenLake.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/frozen_lake) \u003cbr\u003e env tutorial \u003cbr\u003e 环境指南 |\n| 39 | [ising_model](https://github.com/mlii/mfrl/tree/master/examples/ising_model) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) ![marl](https://img.shields.io/badge/-MARL-yellow) | ![original](./dizoo/ising_env/ising_env.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/ising_env) \u003cbr\u003e env tutorial \u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/ising_model_zh.html) |\n| 40 | [taxi](https://www.gymlibrary.dev/environments/toy_text/taxi/) | ![discrete](https://img.shields.io/badge/-discrete-brightgreen) | ![original](./dizoo/taxi/Taxi-v3_episode_0.gif) | [dizoo link](https://github.com/opendilab/DI-engine/tree/main/dizoo/taxi/envs) \u003cbr\u003e [env tutorial](https://di-engine-docs.readthedocs.io/en/latest/13_envs/taxi.html) \u003cbr\u003e [环境指南](https://di-engine-docs.readthedocs.io/zh-cn/latest/13_envs/taxi_zh.html) |\n\n\n\n![discrete](https://img.shields.io/badge/-discrete-brightgreen) means discrete action space\n\n![continuous](https://img.shields.io/badge/-continous-green) means continuous action space\n\n![hybrid](https://img.shields.io/badge/-hybrid-darkgreen) means hybrid (discrete + continuous) action space\n\n![MARL](https://img.shields.io/badge/-MARL-yellow) means multi-agent RL environment\n\n![sparse](https://img.shields.io/badge/-sparse%20reward-orange) means environment which is related to exploration and sparse reward\n\n![offline](https://img.shields.io/badge/-offlineRL-darkblue) means offline RL environment\n\n![IL](https://img.shields.io/badge/-IL/SL-purple) means Imitation Learning or Supervised Learning Dataset\n\n![selfplay](https://img.shields.io/badge/-selfplay-blue) means environment that allows agent VS agent battle\n\nP.S. some enviroments in Atari, such as **MontezumaRevenge**, are also the sparse reward type.\n\n\u003c/details\u003e\n\n### General Data Container: TreeTensor\n\nDI-engine utilizes [TreeTensor](https://github.com/opendilab/DI-treetensor) as the basic data container in various components, which is ease of use and consistent across different code modules such as environment definition, data processing and DRL optimization. Here are some concrete code examples:\n\n- TreeTensor can easily extend all the operations of `torch.Tensor` to nested data:\n\n \u003cdetails close\u003e\n \u003csummary\u003e(Click for Details)\u003c/summary\u003e\n\n ```python\n import treetensor.torch as ttorch\n\n\n # create random tensor\n data = ttorch.randn({'a': (3, 2), 'b': {'c': (3, )}})\n # clone+detach tensor\n data_clone = data.clone().detach()\n # access tree structure like attribute\n a = data.a\n c = data.b.c\n # stack/cat/split\n stacked_data = ttorch.stack([data, data_clone], 0)\n cat_data = ttorch.cat([data, data_clone], 0)\n data, data_clone = ttorch.split(stacked_data, 1)\n # reshape\n data = data.unsqueeze(-1)\n data = data.squeeze(-1)\n flatten_data = data.view(-1)\n # indexing\n data_0 = data[0]\n data_1to2 = data[1:2]\n # execute math calculations\n data = data.sin()\n data.b.c.cos_().clamp_(-1, 1)\n data += data ** 2\n # backward\n data.requires_grad_(True)\n loss = data.arctan().mean()\n loss.backward()\n # print shape\n print(data.shape)\n # result\n # \u003cSize 0x7fbd3346ddc0\u003e\n # ├── 'a' --\u003e torch.Size([1, 3, 2])\n # └── 'b' --\u003e \u003cSize 0x7fbd3346dd00\u003e\n # └── 'c' --\u003e torch.Size([1, 3])\n ```\n\n \u003c/details\u003e\n- TreeTensor can make it simple yet effective to implement classic deep reinforcement learning pipeline\n\n \u003cdetails close\u003e\n \u003csummary\u003e(Click for Details)\u003c/summary\u003e\n\n ```diff\n import torch\n import treetensor.torch as ttorch\n\n B = 4\n\n\n def get_item():\n return {\n 'obs': {\n 'scalar': torch.randn(12),\n 'image': torch.randn(3, 32, 32),\n },\n 'action': torch.randint(0, 10, size=(1,)),\n 'reward': torch.rand(1),\n 'done': False,\n }\n\n\n data = [get_item() for _ in range(B)]\n\n\n # execute `stack` op\n - def stack(data, dim):\n - elem = data[0]\n - if isinstance(elem, torch.Tensor):\n - return torch.stack(data, dim)\n - elif isinstance(elem, dict):\n - return {k: stack([item[k] for item in data], dim) for k in elem.keys()}\n - elif isinstance(elem, bool):\n - return torch.BoolTensor(data)\n - else:\n - raise TypeError(\"not support elem type: {}\".format(type(elem)))\n - stacked_data = stack(data, dim=0)\n + data = [ttorch.tensor(d) for d in data]\n + stacked_data = ttorch.stack(data, dim=0)\n\n # validate\n - assert stacked_data['obs']['image'].shape == (B, 3, 32, 32)\n - assert stacked_data['action'].shape == (B, 1)\n - assert stacked_data['reward'].shape == (B, 1)\n - assert stacked_data['done'].shape == (B,)\n - assert stacked_data['done'].dtype == torch.bool\n + assert stacked_data.obs.image.shape == (B, 3, 32, 32)\n + assert stacked_data.action.shape == (B, 1)\n + assert stacked_data.reward.shape == (B, 1)\n + assert stacked_data.done.shape == (B,)\n + assert stacked_data.done.dtype == torch.bool\n ```\n\n \u003c/details\u003e\n\n## Feedback and Contribution\n\n- [File an issue](https://github.com/opendilab/DI-engine/issues/new/choose) on Github\n- Open or participate in our [forum](https://github.com/opendilab/DI-engine/discussions)\n- Discuss on DI-engine [discord server](https://discord.gg/dkZS2JF56X)\n- Discuss on DI-engine [slack communication channel](https://join.slack.com/t/opendilab/shared_invite/zt-v9tmv4fp-nUBAQEH1_Kuyu_q4plBssQ)\n- Discuss on DI-engine's WeChat group (i.e. add us on WeChat: ding314assist)\n\n \u003cimg src=https://github.com/opendilab/DI-engine/blob/main/assets/wechat.jpeg width=35% /\u003e\n- Contact our email (opendilab@pjlab.org.cn)\n- Contributes to our future plan [Roadmap](https://github.com/opendilab/DI-engine/issues/548)\n\nWe appreciate all the feedbacks and contributions to improve DI-engine, both algorithms and system designs. And `CONTRIBUTING.md` offers some necessary information.\n\n## Supporters\n\n### \u0026#8627; Stargazers\n\n[![Stargazers repo roster for @opendilab/DI-engine](https://reporoster.com/stars/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/stargazers)\n\n### \u0026#8627; Forkers\n\n[![Forkers repo roster for @opendilab/DI-engine](https://reporoster.com/forks/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/network/members)\n\n## Citation\n\n```latex\n@misc{ding,\n title={DI-engine: A Universal AI System/Engine for Decision Intelligence},\n author={Niu, Yazhe and Xu, Jingxin and Pu, Yuan and Nie, Yunpeng and Zhang, Jinouwen and Hu, Shuai and Zhao, Liangxuan and Zhang, Ming and Liu, Yu},\n publisher={GitHub},\n howpublished={\\url{https://github.com/opendilab/DI-engine}},\n year={2021},\n}\n```\n\n## License\n\nDI-engine released under the Apache 2.0 license.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendilab%2Fdi-engine","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopendilab%2Fdi-engine","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendilab%2Fdi-engine/lists"}