{"id":29099333,"url":"https://github.com/typoverflow/flow-rl","last_synced_at":"2025-06-28T16:41:53.116Z","repository":{"id":301673488,"uuid":"964366577","full_name":"typoverflow/flow-rl","owner":"typoverflow","description":"Flow RL is a high-performance RL library with flow and diffusion models.","archived":false,"fork":false,"pushed_at":"2025-05-29T13:00:47.000Z","size":152,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-28T06:25:23.421Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/typoverflow.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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":"2025-04-11T05:27:14.000Z","updated_at":"2025-06-13T13:42:02.000Z","dependencies_parsed_at":"2025-06-28T06:25:46.328Z","dependency_job_id":"cb428242-a5e9-46e6-a002-14d783fe3ff6","html_url":"https://github.com/typoverflow/flow-rl","commit_stats":null,"previous_names":["typoverflow/flow-rl"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/typoverflow/flow-rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/typoverflow%2Fflow-rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/typoverflow%2Fflow-rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/typoverflow%2Fflow-rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/typoverflow%2Fflow-rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/typoverflow","download_url":"https://codeload.github.com/typoverflow/flow-rl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/typoverflow%2Fflow-rl/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262461579,"owners_count":23314973,"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":[],"created_at":"2025-06-28T16:41:50.550Z","updated_at":"2025-06-28T16:41:53.110Z","avatar_url":"https://github.com/typoverflow.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Flow RL\n\n[![PyPI version](https://img.shields.io/pypi/v/flowrl.svg)](https://pypi.org/project/flowrl) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-green.svg)](https://www.python.org/) [![Python 3.8+](https://static.pepy.tech/badge/flowrl)](https://pepy.tech/projects/flowrl)\n\nFlow RL is a high-performance reinforcement learning library, combining modern deep RL algorithms with flow and diffusion models for advanced policy parameterization, planning ability or dynamics modeling. It features:\n- **State-of-the-Art Algorithms and Efficiency**: We provide JAX implementations of SOTA algorithms, such FQL, BDPO, DAC and etc;\n- **Flexible Flow Architectures**: We provide built-in support various types of flow and diffusion models, such as CNFs and DDPM;\n- **Comprehensive Evaluations**: We test the algorithms on commonly adopted benchmark and provide the results.\n\n## 🚀 Installation \u0026 Usage\nCurrently FlowRL is hosted on PyPI and therefore can be installed via `pip install flowrl`. However, we recommend to clone and install the library using the following commands:\n```bash\ngit clone https://github.com/typoverflow/flow-rl.git\ncd flow-rl\npip install -e .\n```\n\nThe entry files are presented in `examples/`. Please refer to the scripts in `scripts/` for how to execute the algorithms.\n\n## 📊 Supported Algorithms\nOffline RL:\n|Algorithm|Location|WandB Report|\n|:---:|:---:|:---:|\n|IQL|`flowrl/agent/iql.py`|[[Performance]](https://wandb.ai/lamda-rl/flow-rl?nw=urvdu9rz7b\u0026panelDisplayName=eval%2Fmean\u0026panelSectionName=eval) [[Full Log]](https://wandb.ai/lamda-rl/flow-rl?nw=urvdu9rz7b)|\n|IVR|`flowrl/agent/ivr.py`|[[Performance]](https://wandb.ai/lamda-rl/flow-rl/panel/nz7r4sj4n?nw=oslzekjlr1q) [[Full Log]](https://wandb.ai/lamda-rl/flow-rl?nw=oslzekjlr1q)|\n|FQL|`flowrl/agent/fql/fql.py`|[[Performance]](https://wandb.ai/lamda-rl/flow-rl?nw=u9y84ki7rdi\u0026panelDisplayName=eval%2Fmean\u0026panelSectionName=eval) [[Full Log]](https://wandb.ai/lamda-rl/flow-rl?nw=u9y84ki7rdi)|\n|DAC|`flowrl/agent/dac.py`|[[Performance]](https://wandb.ai/lamda-rl/flow-rl/panel/nz7r4sj4n?nw=uqr7jg46c5) [[Full Log]](https://wandb.ai/lamda-rl/flow-rl?nw=uqr7jg46c5)|\n|BDPO|`flowrl/agent/bdpo/bdpo.py`|[[Performance]](https://wandb.ai/lamda-rl/flow-rl/panel/nz7r4sj4n?nw=2q8v54gusia) [[Full Log]](https://wandb.ai/lamda-rl/flow-rl?nw=2q8v54gusia)|\n\n## 📝 Citing Flow RL\nIf you use Flow RL in your research, please cite:\n```bibtex\n@software{flow_rl,\n  author       = {Chen-Xiao Gao and Mingjun Cao},\n  title        = {Flow RL: Flow-based Reinforcement Learning Algorithms},\n  year         = 2025,\n  version      = {v0.0.1},\n  url          = {https://github.com/typoverflow/flow-rl}\n}\n```\n\n## 💎 Acknowledgements\nInspired by foundational work from\n- [Jax-CORL](https://github.com/nissymori/JAX-CORL)\n- [DAC](https://github.com/Fang-Lin93/DAC)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftypoverflow%2Fflow-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftypoverflow%2Fflow-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftypoverflow%2Fflow-rl/lists"}