Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

awesome-rl-env-zoo

Last synced: about 21 hours ago
JSON representation

Envs
- Atari
  - The Arcade Learning Environment (ALE)
  - Random Network Distillation (RND)
  - Go-Explore
  - Prediction-Based Rewards (By OpenAI)
  - Official Gym Documentation
  - English - engine-docs.readthedocs.io/zh_CN/latest/13_envs/atari_zh.html))
  - DI-engine
  - tianshou
  - Prediction-Based Rewards (By OpenAI)
- MPE
- SMAC
  - SMAC
  - PyMARL2
  - English - engine-docs.readthedocs.io/zh_CN/latest/13_envs/smac_zh.html))
  - DI-engine
  - RLlib
- MuJoCo
  - Official Gym Documentation
  - English - engine-docs.readthedocs.io/zh_CN/latest/13_envs/mujoco_zh.html))
  - DI-engine
  - ChainerRL
  - mujoco (by DeepMind) - py (by OpenAI)](https://github.com/openai/mujoco-py)
  - Stable Baselines 3 - RM/rl-baselines3-zoo/blob/master/hyperparams/td3.yml) | [PPO](https://github.com/DLR-RM/rl-baselines3-zoo/blob/master/hyperparams/ppo.yml) | [SAC](https://github.com/DLR-RM/rl-baselines3-zoo/blob/master/hyperparams/sac.yml)
Format and Terminology
- Terminology in the description table
  - Learning values across many orders of magnitude
  - Procgen paper - envs vary a lot. You can refer to the radar plot in [bsuite](https://github.com/deepmind/bsuite). | You must control more than one agent at a time. You can refer to [An Overview of Multi-Agent Reinforcement Learning from Game Theoretical Perspective](https://arxiv.org/abs/2011.00583). |

Programming Languages