├── .gitignore ├── LICENSE ├── README.md ├── coma ├── __init__.py ├── components │ ├── __init__.py │ ├── action_selectors.py │ ├── episode_buffer.py │ ├── epsilon_schedules.py │ └── transforms.py ├── config │ ├── algs │ │ ├── coma.yaml │ │ ├── coma_no_ob.yaml │ │ ├── coma_ob.yaml │ │ ├── iql.yaml │ │ ├── iql_beta.yaml │ │ ├── qmix.yaml │ │ ├── qmix_beta.yaml │ │ ├── qtran.yaml │ │ ├── vdn.yaml │ │ └── vdn_beta.yaml │ ├── default.yaml │ └── envs │ │ ├── sc2.yaml │ │ └── sc2_beta.yaml ├── controllers │ ├── __init__.py │ └── basic_controller.py ├── envs │ ├── __init__.py │ └── multiagentenv.py ├── learners │ ├── __init__.py │ ├── coma_learner.py │ ├── q_learner.py │ └── qtran_learner.py ├── main.py ├── modules │ ├── __init__.py │ ├── agents │ │ ├── __init__.py │ │ └── rnn_agent.py │ ├── critics │ │ ├── __init__.py │ │ └── coma.py │ └── mixers │ │ ├── __init__.py │ │ ├── qmix.py │ │ ├── qtran.py │ │ └── vdn.py ├── run.py ├── runners │ ├── __init__.py │ ├── episode_runner.py │ └── parallel_runner.py ├── train_smac.sh └── utils │ ├── dict2namedtuple.py │ ├── logging.py │ ├── rl_utils.py │ └── timehelper.py ├── install_sc2.sh ├── mappo ├── __init__.py ├── algorithms │ ├── __init__.py │ ├── actor_critic.py │ ├── mappo_policy.py │ ├── mappo_trainer.py │ └── utils │ │ ├── act.py │ │ ├── cnn.py │ │ ├── distributions.py │ │ ├── mlp.py │ │ ├── rnn.py │ │ └── util.py ├── config │ ├── __init__.py │ ├── config_default.py │ ├── config_mujoco.py │ └── config_smac.py ├── envs │ ├── __init__.py │ ├── env_wrappers.py │ ├── ma_mujoco │ │ ├── __init__.py │ │ └── multiagent_mujoco │ │ │ ├── __init__.py │ │ │ ├── assets │ │ │ ├── .gitignore │ │ │ ├── __init__.py │ │ │ ├── coupled_half_cheetah.xml │ │ │ ├── manyagent_ant.xml │ │ │ ├── manyagent_ant.xml.template │ │ │ ├── manyagent_ant__stage1.xml │ │ │ ├── manyagent_swimmer.xml.template │ │ │ ├── manyagent_swimmer__bckp2.xml │ │ │ └── manyagent_swimmer_bckp.xml │ │ │ ├── coupled_half_cheetah.py │ │ │ ├── manyagent_ant.py │ │ │ ├── manyagent_swimmer.py │ │ │ ├── mujoco_multi.py │ │ │ ├── multiagentenv.py │ │ │ └── obsk.py │ └── starcraft2 │ │ ├── StarCraft2_Env.py │ │ ├── multiagentenv.py │ │ └── smac_maps.py ├── runner │ └── shared │ │ ├── base_runner.py │ │ ├── mujoco_runner.py │ │ └── smac_runner.py ├── scripts │ ├── __init__.py │ ├── train │ │ ├── __init__.py │ │ ├── train_mujoco.py │ │ └── train_smac.py │ ├── train_mujoco.sh │ └── train_smac.sh └── utils │ ├── __init__.py │ ├── popart.py │ ├── shared_buffer.py │ └── util.py ├── plots ├── coma_smac.png ├── mappo_mujoco.png └── mappo_smac.png └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/README.md -------------------------------------------------------------------------------- /coma/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /coma/components/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /coma/components/action_selectors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/components/action_selectors.py -------------------------------------------------------------------------------- /coma/components/episode_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/components/episode_buffer.py -------------------------------------------------------------------------------- /coma/components/epsilon_schedules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/components/epsilon_schedules.py -------------------------------------------------------------------------------- /coma/components/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/components/transforms.py -------------------------------------------------------------------------------- /coma/config/algs/coma.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/coma.yaml -------------------------------------------------------------------------------- /coma/config/algs/coma_no_ob.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/coma_no_ob.yaml -------------------------------------------------------------------------------- /coma/config/algs/coma_ob.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/coma_ob.yaml -------------------------------------------------------------------------------- /coma/config/algs/iql.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/iql.yaml -------------------------------------------------------------------------------- /coma/config/algs/iql_beta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/iql_beta.yaml -------------------------------------------------------------------------------- /coma/config/algs/qmix.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/qmix.yaml -------------------------------------------------------------------------------- /coma/config/algs/qmix_beta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/qmix_beta.yaml -------------------------------------------------------------------------------- /coma/config/algs/qtran.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/qtran.yaml -------------------------------------------------------------------------------- /coma/config/algs/vdn.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/vdn.yaml -------------------------------------------------------------------------------- /coma/config/algs/vdn_beta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/algs/vdn_beta.yaml -------------------------------------------------------------------------------- /coma/config/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/default.yaml -------------------------------------------------------------------------------- /coma/config/envs/sc2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/envs/sc2.yaml -------------------------------------------------------------------------------- /coma/config/envs/sc2_beta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/config/envs/sc2_beta.yaml -------------------------------------------------------------------------------- /coma/controllers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/controllers/__init__.py -------------------------------------------------------------------------------- /coma/controllers/basic_controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/controllers/basic_controller.py -------------------------------------------------------------------------------- /coma/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/envs/__init__.py -------------------------------------------------------------------------------- /coma/envs/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/envs/multiagentenv.py -------------------------------------------------------------------------------- /coma/learners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/learners/__init__.py -------------------------------------------------------------------------------- /coma/learners/coma_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/learners/coma_learner.py -------------------------------------------------------------------------------- /coma/learners/q_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/learners/q_learner.py -------------------------------------------------------------------------------- /coma/learners/qtran_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/learners/qtran_learner.py -------------------------------------------------------------------------------- /coma/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/main.py -------------------------------------------------------------------------------- /coma/modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /coma/modules/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/agents/__init__.py -------------------------------------------------------------------------------- /coma/modules/agents/rnn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/agents/rnn_agent.py -------------------------------------------------------------------------------- /coma/modules/critics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /coma/modules/critics/coma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/critics/coma.py -------------------------------------------------------------------------------- /coma/modules/mixers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /coma/modules/mixers/qmix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/mixers/qmix.py -------------------------------------------------------------------------------- /coma/modules/mixers/qtran.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/mixers/qtran.py -------------------------------------------------------------------------------- /coma/modules/mixers/vdn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/modules/mixers/vdn.py -------------------------------------------------------------------------------- /coma/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/run.py -------------------------------------------------------------------------------- /coma/runners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/runners/__init__.py -------------------------------------------------------------------------------- /coma/runners/episode_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/runners/episode_runner.py -------------------------------------------------------------------------------- /coma/runners/parallel_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/runners/parallel_runner.py -------------------------------------------------------------------------------- /coma/train_smac.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/train_smac.sh -------------------------------------------------------------------------------- /coma/utils/dict2namedtuple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/utils/dict2namedtuple.py -------------------------------------------------------------------------------- /coma/utils/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/utils/logging.py -------------------------------------------------------------------------------- /coma/utils/rl_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/utils/rl_utils.py -------------------------------------------------------------------------------- /coma/utils/timehelper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/coma/utils/timehelper.py -------------------------------------------------------------------------------- /install_sc2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/install_sc2.sh -------------------------------------------------------------------------------- /mappo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/algorithms/actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/actor_critic.py -------------------------------------------------------------------------------- /mappo/algorithms/mappo_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/mappo_policy.py -------------------------------------------------------------------------------- /mappo/algorithms/mappo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/mappo_trainer.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/act.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/cnn.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/distributions.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/mlp.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/rnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/rnn.py -------------------------------------------------------------------------------- /mappo/algorithms/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/algorithms/utils/util.py -------------------------------------------------------------------------------- /mappo/config/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/config/config_default.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/config/config_default.py -------------------------------------------------------------------------------- /mappo/config/config_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/config/config_mujoco.py -------------------------------------------------------------------------------- /mappo/config/config_smac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/config/config_smac.py -------------------------------------------------------------------------------- /mappo/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/__init__.py -------------------------------------------------------------------------------- /mappo/envs/env_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/env_wrappers.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/__init__.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/.gitignore: -------------------------------------------------------------------------------- 1 | *.auto.xml 2 | -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/coupled_half_cheetah.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/coupled_half_cheetah.xml -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml.template -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant__stage1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant__stage1.xml -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer.xml.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer.xml.template -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer__bckp2.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer__bckp2.xml -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer_bckp.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer_bckp.xml -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/coupled_half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/coupled_half_cheetah.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/manyagent_ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/manyagent_ant.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/manyagent_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/manyagent_swimmer.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/mujoco_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/mujoco_multi.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/multiagentenv.py -------------------------------------------------------------------------------- /mappo/envs/ma_mujoco/multiagent_mujoco/obsk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/ma_mujoco/multiagent_mujoco/obsk.py -------------------------------------------------------------------------------- /mappo/envs/starcraft2/StarCraft2_Env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/starcraft2/StarCraft2_Env.py -------------------------------------------------------------------------------- /mappo/envs/starcraft2/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/starcraft2/multiagentenv.py -------------------------------------------------------------------------------- /mappo/envs/starcraft2/smac_maps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/envs/starcraft2/smac_maps.py -------------------------------------------------------------------------------- /mappo/runner/shared/base_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/runner/shared/base_runner.py -------------------------------------------------------------------------------- /mappo/runner/shared/mujoco_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/runner/shared/mujoco_runner.py -------------------------------------------------------------------------------- /mappo/runner/shared/smac_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/runner/shared/smac_runner.py -------------------------------------------------------------------------------- /mappo/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/scripts/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/scripts/train/train_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/scripts/train/train_mujoco.py -------------------------------------------------------------------------------- /mappo/scripts/train/train_smac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/scripts/train/train_smac.py -------------------------------------------------------------------------------- /mappo/scripts/train_mujoco.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/scripts/train_mujoco.sh -------------------------------------------------------------------------------- /mappo/scripts/train_smac.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/scripts/train_smac.sh -------------------------------------------------------------------------------- /mappo/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mappo/utils/popart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/utils/popart.py -------------------------------------------------------------------------------- /mappo/utils/shared_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/utils/shared_buffer.py -------------------------------------------------------------------------------- /mappo/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/mappo/utils/util.py -------------------------------------------------------------------------------- /plots/coma_smac.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/plots/coma_smac.png -------------------------------------------------------------------------------- /plots/mappo_mujoco.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/plots/mappo_mujoco.png -------------------------------------------------------------------------------- /plots/mappo_smac.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/plots/mappo_smac.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/morning9393/Optimal-Baseline-for-Multi-agent-Policy-Gradients/HEAD/requirements.txt --------------------------------------------------------------------------------