{"id":19195977,"url":"https://github.com/sweep76/bn-mappo-coordination","last_synced_at":"2025-08-11T04:04:26.099Z","repository":{"id":207078686,"uuid":"718378271","full_name":"Sweep76/BN-Mappo-Coordination","owner":"Sweep76","description":"This is the official implementation of Multi-Agent PPO (MAPPO).","archived":false,"fork":false,"pushed_at":"2024-09-28T11:11:49.000Z","size":434,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-23T04:42:30.149Z","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/Sweep76.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-14T00:25:19.000Z","updated_at":"2024-09-28T11:11:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"4b9919ec-0fbf-451a-9f34-c4ea786a1442","html_url":"https://github.com/Sweep76/BN-Mappo-Coordination","commit_stats":null,"previous_names":["sweep76/cs-3101-bn-mappo-coordination","sweep76/bn-mappo-coordination"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Sweep76/BN-Mappo-Coordination","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sweep76%2FBN-Mappo-Coordination","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sweep76%2FBN-Mappo-Coordination/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sweep76%2FBN-Mappo-Coordination/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sweep76%2FBN-Mappo-Coordination/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sweep76","download_url":"https://codeload.github.com/Sweep76/BN-Mappo-Coordination/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sweep76%2FBN-Mappo-Coordination/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269827300,"owners_count":24481501,"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":"2025-08-11T02:00:10.019Z","response_time":75,"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":"2024-11-09T12:12:08.093Z","updated_at":"2025-08-11T04:04:26.032Z","avatar_url":"https://github.com/Sweep76.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BNPG\n\n## Training\n1.  Train fixed DAG topologies with tabular exact policy gradients on Coordination Game\n\n```\ncd Tabular_Coordination_Game\npython run.py\n```\n\n2. Train context-aware DAG topologies with MAPPO on Coordination Game\n\n```\ncd BN_MAPPO_Coordination_Game/onpolicy/scripts/train\npython train_coordination_game.py --graph_type [dummy, dynamic] --threshold [0,1]\n```\n\n3. Train context-aware DAG topologies with MAPPO on Aloha\n\n```\ncd BN_MAPPO_Aloha/onpolicy/scripts/train\npython train_aloha.py --graph_type [dummy, dynamic] --threshold [0,1]\n```\n\n4. Train context-aware DAG topologies with MAPPO on SMAC\n\n```\ncd BN_MAPPO_SMAC/onpolicy/scripts/train\n\n#on 6h_vs_8z, --use_annealing for annealing strategy\npython train_aloha.py train_smac.py --use_annealing --graph_type [dummy, dynamic] --threshold [0,1] \\ \n--alpha 0.1 --env_name StarCraft2 --algorithm_name mappo --use_recurrent_policy \\\n--map_name 6h_vs_8z --n_training_threads 1 --n_rollout_threads 8 --num_mini_batch 1 --episode_length 400 \\\n --num_env_steps 20000000 --ppo_epoch 5 --use_value_active_masks --use_eval --eval_episodes 32 \n\n#on MMM2, --use_annealing for annealing strategy\npython train_aloha.py train_smac.py --use_annealing --graph_type [dummy, dynamic] --threshold [0,1] \\\n--alpha 0.05 --env_name StarCraft2 --algorithm_name mappo --use_recurrent_policy \\\n    --map_name MMM2 --n_training_threads 1 --n_rollout_threads 8 --num_mini_batch 2 --episode_length 400 \\\n    --num_env_steps 20000000 --ppo_epoch 5 --use_value_active_masks --use_eval --eval_episodes 32 \n```\n\n\n\n### Acknowledgement\nThe MAPPO code is based on https://github.com/marlbenchmark/on-policy\n\nThe differentiable DAG sampling code is based on https://github.com/sharpenb/Differentiable-DAG-Sampling\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsweep76%2Fbn-mappo-coordination","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsweep76%2Fbn-mappo-coordination","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsweep76%2Fbn-mappo-coordination/lists"}