{"data":{"slug":"reinflow-reinflow","name":"ReinFlow","tagline":"ReinFlow combines Flow Policy with online reinforcement learning for fine-tuning across various robotic tasks.","github_url":"https://github.com/ReinFlow/ReinFlow","owner":"ReinFlow","repo":"ReinFlow","owner_avatar_url":"https://avatars.githubusercontent.com/u/212894921?v=4","primary_language":"Python","stars":364,"forks":35,"topics":["actorcritic","fine-tuning","finetuning-rl","finetuning-vision-models","flow","flowmatching","locomotion","manipulation","onlinerl","pi0","policygradient","post-training","rl","robot-learning","robotics","visuomotor","vla"],"archived":false,"github_pushed_at":"2026-04-24T22:34:21+00:00","maintenance_label":"Slowing","stars_delta_30d":15,"url":"https://www.graphcanon.com/tools/reinflow-reinflow","markdown_url":"https://www.graphcanon.com/tools/reinflow-reinflow.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/reinflow-reinflow","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=reinflow-reinflow","description":"[NeurIPS 2025] Flow x RL. \"ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning\". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced. ","homepage_url":"https://reinflow.github.io/","license":"MIT","open_issues":9,"watchers":7,"ai_summary":"An open-source project that integrates flow-based models with reinforcement learning techniques to enhance policy tuning in robotics and visuomotor control tasks such as locomotion and manipulation, supporting variability-informed algorithms like Pi0 and GR00TN1.5.","readme_excerpt":"## :rocket:  Installation\nPlease follow the steps in [installation/reinflow-setup.md](./installation/reinflow-setup.md).\n\n---\n\n## :rocket: Quick Start: Reproduce Our Results\nTo fully reproduce our experiments, please refer to [ReproduceExps.md](docs/ReproduceExps.md). \n\nTo download our training data and reproduce the plots in the paper, please refer to [ReproduceFigs.md](docs/ReproduceFigs.md).\n\n---\n\n## License\nThis repository is released under the MIT license. See [LICENSE](LICENSE). \nIf you use our code, we appreciate it if you paste the license at the beginning of the script.","github_created_at":"2025-05-29T13:15:48+00:00","created_at":"2026-07-11T11:42:11.759299+00:00","updated_at":"2026-09-20T06:32:20.427153+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"actorcritic","name":"actorcritic"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"finetuning-rl","name":"finetuning-rl"},{"slug":"flowmatching","name":"flowmatching"},{"slug":"locomotion","name":"locomotion"},{"slug":"manipulation","name":"manipulation"},{"slug":"online-reinforcement-learning","name":"online-reinforcement-learning"},{"slug":"pi0","name":"pi0"}],"trust":{"provenance":{"is_fork":false,"github_id":992630802,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-19T18:28:59.869Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":147,"last_release_at":null,"stars_delta_30d":15,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:42:12.929Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-19T18:29:00.905Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-19T18:29:00.905Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-19T18:29:00.905Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need to fine-tune policies in robotic manipulation or locomotion","Wishing to apply variability-informed algorithms like Pi0 and GR00TN1.5"],"when_not_to_use":["Looking for solutions outside of robotic control tasks","Requiring offline reinforcement learning methods instead"],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:38:14.547Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Integrates flow-based models with reinforcement learning for robotics tasks"}]}}