{"id":31202805,"url":"https://github.com/semitable/seac","last_synced_at":"2025-09-20T14:05:58.880Z","repository":{"id":50723335,"uuid":"303682518","full_name":"semitable/seac","owner":"semitable","description":"The official code base of Shared Experience Actor-Critic (NeurIPS2020)","archived":false,"fork":false,"pushed_at":"2024-02-23T11:20:37.000Z","size":925,"stargazers_count":14,"open_issues_count":4,"forks_count":20,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-02-23T12:31:37.873Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/semitable.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}},"created_at":"2020-10-13T11:36:09.000Z","updated_at":"2024-02-23T11:20:41.000Z","dependencies_parsed_at":"2022-08-30T19:22:23.211Z","dependency_job_id":null,"html_url":"https://github.com/semitable/seac","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/semitable/seac","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/semitable%2Fseac","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/semitable%2Fseac/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/semitable%2Fseac/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/semitable%2Fseac/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/semitable","download_url":"https://codeload.github.com/semitable/seac/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/semitable%2Fseac/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276106042,"owners_count":25586191,"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","status":"online","status_checked_at":"2025-09-20T02:00:10.207Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2025-09-20T14:05:54.676Z","updated_at":"2025-09-20T14:05:58.873Z","avatar_url":"https://github.com/semitable.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Shared Experience Actor Critic\n\nThis repository is the official implementation of [Shared Experience Actor Critic](https://arxiv.org/abs/2006.07169). \n\n## Requirements\n\nFor the experiments in LBF and RWARE, please install from:\n- [Level Based Foraging Official Repo](https://github.com/uoe-agents/lb-foraging)\n- [Multi-Robot Warehouse Official Repo](https://github.com/uoe-agents/robotic-warehouse)\n\nAlso requires, PyTorch 1.6+\n\n## Training - SEAC\nTo train the agents in the paper, navigate to the seac directory:\n```\ncd seac\n```\n\nAnd run:\n\n```train\npython train.py with \u003cenv config\u003e\n```\n\nValid environment configs are: \n- `env_name=Foraging-15x15-3p-4f-v0 time_limit=25`\n- ...\n- `env_name=Foraging-12x12-2p-1f-v0 time_limit=25` or any other foraging environment size/configuration.\n- `env_name=rware-tiny-2ag-v1 time_limit=500` \n- `env_name=rware-tiny-4ag-v1 time_limit=500` \n- ...\n- `env_name=rware-tiny-2ag-hard-v1 time_limit=500` or any other rware environment size/configuration.\n## Training - SEQL\n\nTo train the agents in the paper, navigate to the seac directory:\n```\ncd seql\n```\n\nAnd run the training script. Possible options are: \n- `python lbf_train.py --env Foraging-12x12-2p-1f-v0` \n- ...\n- `python lbf_train.py --env Foraging-15x15-3p-4f-v0` or any other foraging environment size/configuration.\n- `python rware_train.py --env \"rware-tiny-2ag-v1\"`\n- ...\n- `python rware_train.py --env \"rware-tiny-4ag-v1\"`or any other rware environment size/configuration.\n\n## Evaluation/Visualization - SEAC\n\nTo load and render the pretrained models in SEAC, run in the seac directory\n\n```eval\npython evaluate.py\n```\n\n## Citation\n```\n@inproceedings{christianos2020shared,\n  title={Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning},\n  author={Christianos, Filippos and Sch{\\\"a}fer, Lukas and Albrecht, Stefano V},\n  booktitle = {Advances in Neural Information Processing Systems},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsemitable%2Fseac","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsemitable%2Fseac","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsemitable%2Fseac/lists"}