├── .gitignore ├── LICENSE ├── README.md ├── install.sh ├── install_grf.sh ├── install_mujoco.sh ├── install_pettingzoo.sh ├── install_sc2.sh ├── media ├── bound.png ├── cooperative-break-through.gif ├── serve-pass-and-shoot.gif └── vis_bound.png ├── onpolicy ├── __init__.py ├── algorithms │ ├── __init__.py │ ├── r_mappo │ │ ├── __init__.py │ │ ├── algorithm │ │ │ ├── rMAPPOPolicy.py │ │ │ ├── rMultiMAPPOPolicy.py │ │ │ └── r_actor_critic.py │ │ └── r_mappo.py │ └── utils │ │ ├── act.py │ │ ├── cnn.py │ │ ├── distributions.py │ │ ├── mlp.py │ │ ├── popart.py │ │ ├── rnn.py │ │ ├── tune_constant.py │ │ └── util.py ├── config.py ├── config │ ├── grf.yaml │ ├── mpe.yaml │ ├── mujoco.yaml │ ├── pettingzoo.yaml │ └── smac.yaml ├── envs │ ├── __init__.py │ ├── env_wrappers.py │ ├── grf │ │ ├── grf_env.py │ │ ├── multiagentenv.py │ │ ├── raw_feature_process.py │ │ ├── reward_process.py │ │ ├── scenarios │ │ │ ├── 11_vs_11_competition.py │ │ │ ├── 11_vs_11_easy_stochastic.py │ │ │ ├── 11_vs_11_hard_stochastic.py │ │ │ ├── 11_vs_11_kaggle.py │ │ │ ├── 11_vs_11_stochastic.py │ │ │ ├── 1_vs_1_easy.py │ │ │ ├── 5_vs_5.py │ │ │ ├── 5_vs_5_easy.py │ │ │ ├── 5_vs_5_hard.py │ │ │ ├── 5_vs_5_medium.py │ │ │ ├── __init__.py │ │ │ ├── academy_3_vs_1_with_keeper.py │ │ │ ├── academy_corner.py │ │ │ ├── academy_counterattack_easy.py │ │ │ ├── academy_counterattack_hard.py │ │ │ ├── academy_empty_goal.py │ │ │ ├── academy_empty_goal_close.py │ │ │ ├── academy_pass_and_shoot_with_keeper.py │ │ │ ├── academy_run_pass_and_shoot_with_keeper.py │ │ │ ├── academy_run_to_score.py │ │ │ ├── academy_run_to_score_with_keeper.py │ │ │ ├── academy_single_goal_versus_lazy.py │ │ │ ├── test_example_multiagent.py │ │ │ └── tests │ │ │ │ ├── 11_vs_11_deterministic.py │ │ │ │ ├── 11_vs_11_easy_deterministic.py │ │ │ │ ├── 11_vs_11_hard_deterministic.py │ │ │ │ ├── 11_vs_11_single_goal_deterministic.py │ │ │ │ ├── 11_vs_11_single_goal_stochastic.py │ │ │ │ ├── 11_vs_4_offence_deterministic.py │ │ │ │ ├── 11_vs_4_offence_stochastic.py │ │ │ │ ├── __init__.py │ │ │ │ ├── corner_test.py │ │ │ │ ├── goal_test.py │ │ │ │ ├── keeper_test.py │ │ │ │ ├── kickoff_for_goal_loosing_team_test.py │ │ │ │ ├── multiagent_wrapper.py │ │ │ │ ├── offside_test.py │ │ │ │ ├── penalty.py │ │ │ │ ├── second_half.py │ │ │ │ └── symmetric.py │ │ └── stats_process.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 │ ├── mpe │ │ ├── MPE_env.py │ │ ├── __init__.py │ │ ├── core.py │ │ ├── environment.py │ │ ├── multi_discrete.py │ │ ├── rendering.py │ │ ├── scenario.py │ │ └── scenarios │ │ │ ├── __init__.py │ │ │ ├── simple_reference.py │ │ │ └── simple_spread.py │ ├── pettingzoo │ │ ├── multiagentenv.py │ │ └── pettingzoo_env.py │ └── starcraft2 │ │ ├── StarCraft2_Env.py │ │ ├── multiagentenv.py │ │ └── smac_maps.py ├── exp_utils │ ├── __init__.py │ ├── aim_ops.py │ ├── args_utils.py │ └── experiment.py ├── runner │ ├── base_runner.py │ ├── grf_runner.py │ ├── mpe_runner.py │ ├── mujoco_runner.py │ ├── pettingzoo_runner.py │ └── smac_runner.py ├── scripts │ ├── __init__.py │ └── train │ │ ├── __init__.py │ │ ├── train_mpe.py │ │ ├── train_mujoco.py │ │ ├── train_pettingzoo.py │ │ └── train_smac.py ├── train_utils │ ├── __init__.py │ └── setup_seed.py └── utils │ ├── __init__.py │ ├── shared_buffer.py │ ├── util.py │ └── valuenorm.py ├── run_scripts ├── GRF │ └── 5_vs_5.sh ├── MUJOCO │ ├── ant.sh │ ├── halfcheetah.sh │ ├── hopper.sh │ ├── humanoid.sh │ ├── humanoid_standup.sh │ └── walker2d.sh ├── PettingZoo │ ├── multiwalker.sh │ ├── simple_reference.sh │ └── simple_spread.sh └── SMAC │ ├── 10m_vs_11m.sh │ ├── 27m_vs_30m.sh │ ├── 2c_vs_64zg.sh │ ├── 3s5z.sh │ ├── 3s5z_vs_3s6z.sh │ ├── 3s_vs_5z.sh │ ├── 5m_vs_6m.sh │ ├── 6h_vs_8z.sh │ ├── 8m_vs_9m.sh │ ├── MMM.sh │ ├── MMM2.sh │ └── corridor.sh └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/README.md -------------------------------------------------------------------------------- /install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/install.sh -------------------------------------------------------------------------------- /install_grf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/install_grf.sh -------------------------------------------------------------------------------- /install_mujoco.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/install_mujoco.sh -------------------------------------------------------------------------------- /install_pettingzoo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/install_pettingzoo.sh -------------------------------------------------------------------------------- /install_sc2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/install_sc2.sh -------------------------------------------------------------------------------- /media/bound.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/media/bound.png -------------------------------------------------------------------------------- /media/cooperative-break-through.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/media/cooperative-break-through.gif -------------------------------------------------------------------------------- /media/serve-pass-and-shoot.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/media/serve-pass-and-shoot.gif -------------------------------------------------------------------------------- /media/vis_bound.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/media/vis_bound.png -------------------------------------------------------------------------------- /onpolicy/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/__init__.py -------------------------------------------------------------------------------- /onpolicy/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/algorithm/rMAPPOPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/r_mappo/algorithm/rMAPPOPolicy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/algorithm/rMultiMAPPOPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/r_mappo/algorithm/rMultiMAPPOPolicy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/algorithm/r_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/r_mappo/algorithm/r_actor_critic.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/r_mappo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/r_mappo/r_mappo.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/act.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/cnn.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/distributions.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/mlp.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/popart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/popart.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/rnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/rnn.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/tune_constant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/tune_constant.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/algorithms/utils/util.py -------------------------------------------------------------------------------- /onpolicy/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config.py -------------------------------------------------------------------------------- /onpolicy/config/grf.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config/grf.yaml -------------------------------------------------------------------------------- /onpolicy/config/mpe.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config/mpe.yaml -------------------------------------------------------------------------------- /onpolicy/config/mujoco.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config/mujoco.yaml -------------------------------------------------------------------------------- /onpolicy/config/pettingzoo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config/pettingzoo.yaml -------------------------------------------------------------------------------- /onpolicy/config/smac.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/config/smac.yaml -------------------------------------------------------------------------------- /onpolicy/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/env_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/env_wrappers.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/grf_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/grf_env.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/multiagentenv.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/raw_feature_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/raw_feature_process.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/reward_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/reward_process.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/11_vs_11_competition.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/11_vs_11_competition.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/11_vs_11_easy_stochastic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/11_vs_11_easy_stochastic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/11_vs_11_hard_stochastic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/11_vs_11_hard_stochastic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/11_vs_11_kaggle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/11_vs_11_kaggle.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/11_vs_11_stochastic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/11_vs_11_stochastic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/1_vs_1_easy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/1_vs_1_easy.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/5_vs_5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/5_vs_5.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/5_vs_5_easy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/5_vs_5_easy.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/5_vs_5_hard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/5_vs_5_hard.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/5_vs_5_medium.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/5_vs_5_medium.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_3_vs_1_with_keeper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_3_vs_1_with_keeper.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_corner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_corner.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_counterattack_easy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_counterattack_easy.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_counterattack_hard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_counterattack_hard.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_empty_goal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_empty_goal.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_empty_goal_close.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_empty_goal_close.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_pass_and_shoot_with_keeper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_pass_and_shoot_with_keeper.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_run_pass_and_shoot_with_keeper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_run_pass_and_shoot_with_keeper.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_run_to_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_run_to_score.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_run_to_score_with_keeper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_run_to_score_with_keeper.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/academy_single_goal_versus_lazy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/academy_single_goal_versus_lazy.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/test_example_multiagent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/test_example_multiagent.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_11_deterministic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_11_deterministic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_11_easy_deterministic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_11_easy_deterministic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_11_hard_deterministic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_11_hard_deterministic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_11_single_goal_deterministic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_11_single_goal_deterministic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_11_single_goal_stochastic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_11_single_goal_stochastic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_4_offence_deterministic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_4_offence_deterministic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/11_vs_4_offence_stochastic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/11_vs_4_offence_stochastic.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/corner_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/corner_test.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/goal_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/goal_test.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/keeper_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/keeper_test.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/kickoff_for_goal_loosing_team_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/kickoff_for_goal_loosing_team_test.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/multiagent_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/multiagent_wrapper.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/offside_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/offside_test.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/penalty.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/penalty.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/second_half.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/second_half.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/scenarios/tests/symmetric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/scenarios/tests/symmetric.py -------------------------------------------------------------------------------- /onpolicy/envs/grf/stats_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/grf/stats_process.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/.gitignore: -------------------------------------------------------------------------------- 1 | *.auto.xml 2 | -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/coupled_half_cheetah.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/coupled_half_cheetah.xml -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant.xml.template -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant__stage1.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_ant__stage1.xml -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer.xml.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer.xml.template -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer__bckp2.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer__bckp2.xml -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer_bckp.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/assets/manyagent_swimmer_bckp.xml -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/coupled_half_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/coupled_half_cheetah.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/manyagent_ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/manyagent_ant.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/manyagent_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/manyagent_swimmer.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/mujoco_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/mujoco_multi.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/multiagentenv.py -------------------------------------------------------------------------------- /onpolicy/envs/ma_mujoco/multiagent_mujoco/obsk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/ma_mujoco/multiagent_mujoco/obsk.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/MPE_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/MPE_env.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /onpolicy/envs/mpe/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/core.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/environment.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/multi_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/multi_discrete.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/rendering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/rendering.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenario.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/scenario.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/scenarios/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_reference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/scenarios/simple_reference.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_spread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/mpe/scenarios/simple_spread.py -------------------------------------------------------------------------------- /onpolicy/envs/pettingzoo/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/pettingzoo/multiagentenv.py -------------------------------------------------------------------------------- /onpolicy/envs/pettingzoo/pettingzoo_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/pettingzoo/pettingzoo_env.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/StarCraft2_Env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/starcraft2/StarCraft2_Env.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/starcraft2/multiagentenv.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/smac_maps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/envs/starcraft2/smac_maps.py -------------------------------------------------------------------------------- /onpolicy/exp_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/exp_utils/__init__.py -------------------------------------------------------------------------------- /onpolicy/exp_utils/aim_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/exp_utils/aim_ops.py -------------------------------------------------------------------------------- /onpolicy/exp_utils/args_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/exp_utils/args_utils.py -------------------------------------------------------------------------------- /onpolicy/exp_utils/experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/exp_utils/experiment.py -------------------------------------------------------------------------------- /onpolicy/runner/base_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/base_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/grf_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/grf_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/mpe_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/mpe_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/mujoco_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/mujoco_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/pettingzoo_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/pettingzoo_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/smac_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/runner/smac_runner.py -------------------------------------------------------------------------------- /onpolicy/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/scripts/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_mpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/scripts/train/train_mpe.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/scripts/train/train_mujoco.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_pettingzoo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/scripts/train/train_pettingzoo.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_smac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/scripts/train/train_smac.py -------------------------------------------------------------------------------- /onpolicy/train_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/train_utils/__init__.py -------------------------------------------------------------------------------- /onpolicy/train_utils/setup_seed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/train_utils/setup_seed.py -------------------------------------------------------------------------------- /onpolicy/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/utils/shared_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/utils/shared_buffer.py -------------------------------------------------------------------------------- /onpolicy/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/utils/util.py -------------------------------------------------------------------------------- /onpolicy/utils/valuenorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/onpolicy/utils/valuenorm.py -------------------------------------------------------------------------------- /run_scripts/GRF/5_vs_5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/GRF/5_vs_5.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/ant.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/ant.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/halfcheetah.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/halfcheetah.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/hopper.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/hopper.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/humanoid.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/humanoid.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/humanoid_standup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/humanoid_standup.sh -------------------------------------------------------------------------------- /run_scripts/MUJOCO/walker2d.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/MUJOCO/walker2d.sh -------------------------------------------------------------------------------- /run_scripts/PettingZoo/multiwalker.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/PettingZoo/multiwalker.sh -------------------------------------------------------------------------------- /run_scripts/PettingZoo/simple_reference.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/PettingZoo/simple_reference.sh -------------------------------------------------------------------------------- /run_scripts/PettingZoo/simple_spread.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/PettingZoo/simple_spread.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/10m_vs_11m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/10m_vs_11m.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/27m_vs_30m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/27m_vs_30m.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/2c_vs_64zg.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/2c_vs_64zg.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/3s5z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/3s5z.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/3s5z_vs_3s6z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/3s5z_vs_3s6z.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/3s_vs_5z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/3s_vs_5z.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/5m_vs_6m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/5m_vs_6m.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/6h_vs_8z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/6h_vs_8z.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/8m_vs_9m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/8m_vs_9m.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/MMM.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/MMM.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/MMM2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/MMM2.sh -------------------------------------------------------------------------------- /run_scripts/SMAC/corridor.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/run_scripts/SMAC/corridor.sh -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xihuai18/A2PO-ICLR2023/HEAD/setup.py --------------------------------------------------------------------------------