{"id":16936801,"url":"https://github.com/chendrag/sfbc","last_synced_at":"2025-03-22T12:32:07.514Z","repository":{"id":65957836,"uuid":"603432117","full_name":"ChenDRAG/SfBC","owner":"ChenDRAG","description":"Codes accompanying the paper \"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling\" (ICLR 2023) https://arxiv.org/abs/2209.14548","archived":false,"fork":false,"pushed_at":"2023-10-11T09:15:15.000Z","size":17530,"stargazers_count":38,"open_issues_count":0,"forks_count":5,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-18T11:11:26.237Z","etag":null,"topics":["diffusion","expressive","generative","offline","reinforcement-learning","score-based"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ChenDRAG.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-02-18T13:50:29.000Z","updated_at":"2025-01-17T16:07:18.000Z","dependencies_parsed_at":"2024-01-14T16:24:41.004Z","dependency_job_id":null,"html_url":"https://github.com/ChenDRAG/SfBC","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenDRAG%2FSfBC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenDRAG%2FSfBC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenDRAG%2FSfBC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenDRAG%2FSfBC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenDRAG","download_url":"https://codeload.github.com/ChenDRAG/SfBC/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244959444,"owners_count":20538625,"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":["diffusion","expressive","generative","offline","reinforcement-learning","score-based"],"created_at":"2024-10-13T20:57:56.461Z","updated_at":"2025-03-22T12:32:04.840Z","avatar_url":"https://github.com/ChenDRAG.png","language":"Python","readme":"# Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling\n\nThis is a pytorch implementation of SfBC: [Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling](https://arxiv.org/abs/2209.14548).\n\n![Algorithm Overview](https://github.com/ChenDRAG/SfBC/blob/master/overview.PNG)\n\n\\* **For diffusion-based offline RL, we recommend trying our subsequent work, QGPO([paper](https://arxiv.org/abs/2304.12824); [Github](https://github.com/ChenDRAG/CEP-energy-guided-diffusion)). Compared with SfBC, QGPO has improved computational efficiency and noticeably better performance.**\n\n## Requirements\n\n- See conda requirements in `requirements.yml`\n\n## Quick Start\nTrain the behavior model:\n\n```shell\n$ python3 train_behavior.py\n```\n\nTrain the critic model and plot evaluation scores with tensorboard:\n\n```shell\n$ python3 train_critic.py\n```\n\nEvaluation only:\n\n```shell\n$ python3 evaluation.py\n```\n\n## Citing\nIf you find this code release useful, please reference in your paper:\n```\n@inproceedings{\nchen2023offline,\ntitle={Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling},\nauthor={Huayu Chen and Cheng Lu and Chengyang Ying and Hang Su and Jun Zhu},\nbooktitle={The Eleventh International Conference on Learning Representations },\nyear={2023},\n}\n```\n\n## Note\n+ Contact us at: chenhuay17@gmail.com if you have any question.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchendrag%2Fsfbc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchendrag%2Fsfbc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchendrag%2Fsfbc/lists"}