├── .gitignore ├── LICENSE ├── README.md ├── environment.yaml ├── onpolicy ├── __init__.py ├── algorithms │ ├── __init__.py │ ├── happo │ │ ├── happo_trainer.py │ │ └── policy.py │ ├── hatrpo │ │ ├── hatrpo_trainer.py │ │ └── policy.py │ ├── mat │ │ ├── algorithm │ │ │ ├── ma_transformer.py │ │ │ └── transformer_policy.py │ │ └── mat_trainer.py │ ├── r_mappo │ │ ├── __init__.py │ │ ├── algorithm │ │ │ ├── rMAPPOPolicy.py │ │ │ └── r_actor_critic.py │ │ └── r_mappo.py │ └── utils │ │ ├── act.py │ │ ├── cnn.py │ │ ├── distributions.py │ │ ├── mlp.py │ │ ├── popart.py │ │ ├── popart_hatrpo.py │ │ ├── rnn.py │ │ ├── transformer_act.py │ │ └── util.py ├── config.py ├── envs │ ├── __init__.py │ ├── env_wrappers.py │ ├── football │ │ ├── .DS_Store │ │ └── Football_Env.py │ ├── hanabi │ │ ├── CMakeLists.txt │ │ ├── Hanabi_Env.py │ │ ├── __init__.py │ │ ├── clean_all.sh │ │ ├── hanabi_lib │ │ │ ├── CMakeLists.txt │ │ │ ├── canonical_encoders.cc │ │ │ ├── canonical_encoders.h │ │ │ ├── hanabi_card.cc │ │ │ ├── hanabi_card.h │ │ │ ├── hanabi_game.cc │ │ │ ├── hanabi_game.h │ │ │ ├── hanabi_hand.cc │ │ │ ├── hanabi_hand.h │ │ │ ├── hanabi_history_item.cc │ │ │ ├── hanabi_history_item.h │ │ │ ├── hanabi_move.cc │ │ │ ├── hanabi_move.h │ │ │ ├── hanabi_observation.cc │ │ │ ├── hanabi_observation.h │ │ │ ├── hanabi_state.cc │ │ │ ├── hanabi_state.h │ │ │ ├── observation_encoder.h │ │ │ ├── util.cc │ │ │ └── util.h │ │ ├── pyhanabi.cc │ │ ├── pyhanabi.h │ │ └── pyhanabi.py │ ├── mpe │ │ ├── MPE_env.py │ │ ├── __init__.py │ │ ├── core.py │ │ ├── environment.py │ │ ├── multi_discrete.py │ │ ├── rendering.py │ │ ├── scenario.py │ │ └── scenarios │ │ │ ├── __init__.py │ │ │ ├── simple_adversary.py │ │ │ ├── simple_attack.py │ │ │ ├── simple_crypto.py │ │ │ ├── simple_crypto_display.py │ │ │ ├── simple_push.py │ │ │ ├── simple_reference.py │ │ │ ├── simple_speaker_listener.py │ │ │ ├── simple_spread.py │ │ │ ├── simple_tag.py │ │ │ └── simple_world_comm.py │ └── starcraft2 │ │ ├── SMACv2.py │ │ ├── SMACv2_modified.py │ │ ├── StarCraft2_Env.py │ │ ├── StarCraft2v2 │ │ ├── distributions.py │ │ ├── starcraft2.py │ │ └── wrapper.py │ │ ├── multiagentenv.py │ │ └── smac_maps.py ├── runner │ ├── separated │ │ ├── base_runner.py │ │ ├── mpe_runner.py │ │ └── smac_runner.py │ └── shared │ │ ├── base_runner.py │ │ ├── football_runner.py │ │ ├── hanabi_runner_forward.py │ │ ├── mpe_runner.py │ │ └── smac_runner.py ├── scripts │ ├── __init__.py │ ├── eval │ │ └── eval_hanabi.py │ ├── eval_hanabi_forward.sh │ ├── render │ │ ├── render_football.py │ │ └── render_mpe.py │ ├── render_football.sh │ ├── render_mpe.sh │ ├── train │ │ ├── __init__.py │ │ ├── train_football.py │ │ ├── train_hanabi_forward.py │ │ ├── train_mpe.py │ │ └── train_smac.py │ ├── train_football_scripts │ │ ├── train_football_3v1.sh │ │ ├── train_football_ca_easy.sh │ │ ├── train_football_ca_hard.sh │ │ ├── train_football_corner.sh │ │ ├── train_football_rp.sh │ │ └── train_football_rps.sh │ ├── train_hanabi_forward.sh │ ├── train_mpe_scripts │ │ ├── train_mpe_comm.sh │ │ ├── train_mpe_reference.sh │ │ └── train_mpe_spread.sh │ ├── train_other_algo │ │ ├── train_happo.sh │ │ ├── train_hatrpo.sh │ │ ├── train_mat.sh │ │ └── train_mat_dec.sh │ ├── train_smac_scripts │ │ ├── train_smac_10m_vs_11m.sh │ │ ├── train_smac_1c3s5z.sh │ │ ├── train_smac_25m.sh │ │ ├── train_smac_27m_vs_30m.sh │ │ ├── train_smac_2c_vs_64zg.sh │ │ ├── train_smac_2m_vs_1z.sh │ │ ├── train_smac_2s_vs_1sc.sh │ │ ├── train_smac_3m.sh │ │ ├── train_smac_3s5z.sh │ │ ├── train_smac_3s5z_vs_3s6z.sh │ │ ├── train_smac_3s_vs_3z.sh │ │ ├── train_smac_3s_vs_4z.sh │ │ ├── train_smac_3s_vs_5z.sh │ │ ├── train_smac_5m_vs_6m.sh │ │ ├── train_smac_6h_vs_8z.sh │ │ ├── train_smac_8m.sh │ │ ├── train_smac_8m_vs_9m.sh │ │ ├── train_smac_MMM.sh │ │ ├── train_smac_MMM2.sh │ │ ├── train_smac_bane_vs_bane.sh │ │ ├── train_smac_baneling.sh │ │ └── train_smac_corridor.sh │ └── train_smacv2_scripts │ │ ├── train_protoss_10v10.sh │ │ ├── train_protoss_10v11.sh │ │ ├── train_protoss_20v20.sh │ │ ├── train_protoss_20v23.sh │ │ ├── train_protoss_5v5.sh │ │ ├── train_terran_10v10.sh │ │ ├── train_terran_10v11.sh │ │ ├── train_terran_20v20.sh │ │ ├── train_terran_20v23.sh │ │ ├── train_terran_5v5.sh │ │ ├── train_zerg_10v10.sh │ │ ├── train_zerg_10v11.sh │ │ ├── train_zerg_20v20.sh │ │ ├── train_zerg_20v23.sh │ │ └── train_zerg_5v5.sh └── utils │ ├── __init__.py │ ├── multi_discrete.py │ ├── separated_buffer.py │ ├── shared_buffer.py │ ├── util.py │ └── valuenorm.py ├── requirements.txt └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/README.md -------------------------------------------------------------------------------- /environment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/environment.yaml -------------------------------------------------------------------------------- /onpolicy/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/__init__.py -------------------------------------------------------------------------------- /onpolicy/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/algorithms/happo/happo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/happo/happo_trainer.py -------------------------------------------------------------------------------- /onpolicy/algorithms/happo/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/happo/policy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/hatrpo/hatrpo_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/hatrpo/hatrpo_trainer.py -------------------------------------------------------------------------------- /onpolicy/algorithms/hatrpo/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/hatrpo/policy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/mat/algorithm/ma_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/mat/algorithm/ma_transformer.py -------------------------------------------------------------------------------- /onpolicy/algorithms/mat/algorithm/transformer_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/mat/algorithm/transformer_policy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/mat/mat_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/mat/mat_trainer.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/algorithm/rMAPPOPolicy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/r_mappo/algorithm/rMAPPOPolicy.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/algorithm/r_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/r_mappo/algorithm/r_actor_critic.py -------------------------------------------------------------------------------- /onpolicy/algorithms/r_mappo/r_mappo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/r_mappo/r_mappo.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/act.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/cnn.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/distributions.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/mlp.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/popart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/popart.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/popart_hatrpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/popart_hatrpo.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/rnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/rnn.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/transformer_act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/transformer_act.py -------------------------------------------------------------------------------- /onpolicy/algorithms/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/algorithms/utils/util.py -------------------------------------------------------------------------------- /onpolicy/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/config.py -------------------------------------------------------------------------------- /onpolicy/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/env_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/env_wrappers.py -------------------------------------------------------------------------------- /onpolicy/envs/football/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/football/.DS_Store -------------------------------------------------------------------------------- /onpolicy/envs/football/Football_Env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/football/Football_Env.py -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/CMakeLists.txt -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/Hanabi_Env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/Hanabi_Env.py -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/clean_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/clean_all.sh -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/CMakeLists.txt -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/canonical_encoders.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/canonical_encoders.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/canonical_encoders.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/canonical_encoders.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_card.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_card.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_card.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_card.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_game.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_game.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_game.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_game.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_hand.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_hand.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_hand.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_hand.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_history_item.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_history_item.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_history_item.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_history_item.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_move.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_move.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_move.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_move.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_observation.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_observation.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_observation.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_observation.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_state.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_state.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/hanabi_state.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/hanabi_state.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/observation_encoder.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/observation_encoder.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/util.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/util.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/hanabi_lib/util.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/hanabi_lib/util.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/pyhanabi.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/pyhanabi.cc -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/pyhanabi.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/pyhanabi.h -------------------------------------------------------------------------------- /onpolicy/envs/hanabi/pyhanabi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/hanabi/pyhanabi.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/MPE_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/MPE_env.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /onpolicy/envs/mpe/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/core.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/environment.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/multi_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/multi_discrete.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/rendering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/rendering.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenario.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenario.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/__init__.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_adversary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_adversary.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_attack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_attack.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_crypto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_crypto.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_crypto_display.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_crypto_display.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_push.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_push.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_reference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_reference.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_speaker_listener.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_speaker_listener.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_spread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_spread.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_tag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_tag.py -------------------------------------------------------------------------------- /onpolicy/envs/mpe/scenarios/simple_world_comm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/mpe/scenarios/simple_world_comm.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/SMACv2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/SMACv2.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/SMACv2_modified.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/SMACv2_modified.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/StarCraft2_Env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/StarCraft2_Env.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/StarCraft2v2/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/StarCraft2v2/distributions.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/StarCraft2v2/starcraft2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/StarCraft2v2/starcraft2.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/StarCraft2v2/wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/StarCraft2v2/wrapper.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/multiagentenv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/multiagentenv.py -------------------------------------------------------------------------------- /onpolicy/envs/starcraft2/smac_maps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/envs/starcraft2/smac_maps.py -------------------------------------------------------------------------------- /onpolicy/runner/separated/base_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/separated/base_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/separated/mpe_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/separated/mpe_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/separated/smac_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/separated/smac_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/shared/base_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/shared/base_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/shared/football_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/shared/football_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/shared/hanabi_runner_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/shared/hanabi_runner_forward.py -------------------------------------------------------------------------------- /onpolicy/runner/shared/mpe_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/shared/mpe_runner.py -------------------------------------------------------------------------------- /onpolicy/runner/shared/smac_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/runner/shared/smac_runner.py -------------------------------------------------------------------------------- /onpolicy/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/scripts/eval/eval_hanabi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/eval/eval_hanabi.py -------------------------------------------------------------------------------- /onpolicy/scripts/eval_hanabi_forward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/eval_hanabi_forward.sh -------------------------------------------------------------------------------- /onpolicy/scripts/render/render_football.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/render/render_football.py -------------------------------------------------------------------------------- /onpolicy/scripts/render/render_mpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/render/render_mpe.py -------------------------------------------------------------------------------- /onpolicy/scripts/render_football.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/render_football.sh -------------------------------------------------------------------------------- /onpolicy/scripts/render_mpe.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/render_mpe.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_football.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train/train_football.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_hanabi_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train/train_hanabi_forward.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_mpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train/train_mpe.py -------------------------------------------------------------------------------- /onpolicy/scripts/train/train_smac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train/train_smac.py -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_3v1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_3v1.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_ca_easy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_ca_easy.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_ca_hard.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_ca_hard.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_corner.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_corner.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_rp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_rp.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_football_scripts/train_football_rps.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_football_scripts/train_football_rps.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_hanabi_forward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_hanabi_forward.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_mpe_scripts/train_mpe_comm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_mpe_scripts/train_mpe_comm.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_mpe_scripts/train_mpe_reference.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_mpe_scripts/train_mpe_reference.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_mpe_scripts/train_mpe_spread.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_mpe_scripts/train_mpe_spread.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_other_algo/train_happo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_other_algo/train_happo.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_other_algo/train_hatrpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_other_algo/train_hatrpo.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_other_algo/train_mat.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_other_algo/train_mat.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_other_algo/train_mat_dec.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_other_algo/train_mat_dec.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_10m_vs_11m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_10m_vs_11m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_1c3s5z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_1c3s5z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_25m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_25m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_27m_vs_30m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_27m_vs_30m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_2c_vs_64zg.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_2c_vs_64zg.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_2m_vs_1z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_2m_vs_1z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_2s_vs_1sc.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_2s_vs_1sc.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3s5z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3s5z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3s5z_vs_3s6z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3s5z_vs_3s6z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_3z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_3z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_4z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_4z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_5z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_3s_vs_5z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_5m_vs_6m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_5m_vs_6m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_6h_vs_8z.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_6h_vs_8z.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_8m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_8m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_8m_vs_9m.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_8m_vs_9m.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_MMM.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_MMM.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_MMM2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_MMM2.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_bane_vs_bane.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_bane_vs_bane.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_baneling.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_baneling.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smac_scripts/train_smac_corridor.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smac_scripts/train_smac_corridor.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_protoss_10v10.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_protoss_10v10.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_protoss_10v11.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_protoss_10v11.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_protoss_20v20.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_protoss_20v20.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_protoss_20v23.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_protoss_20v23.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_protoss_5v5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_protoss_5v5.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_terran_10v10.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_terran_10v10.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_terran_10v11.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_terran_10v11.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_terran_20v20.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_terran_20v20.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_terran_20v23.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_terran_20v23.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_terran_5v5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_terran_5v5.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_zerg_10v10.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_zerg_10v10.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_zerg_10v11.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_zerg_10v11.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_zerg_20v20.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_zerg_20v20.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_zerg_20v23.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_zerg_20v23.sh -------------------------------------------------------------------------------- /onpolicy/scripts/train_smacv2_scripts/train_zerg_5v5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/scripts/train_smacv2_scripts/train_zerg_5v5.sh -------------------------------------------------------------------------------- /onpolicy/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /onpolicy/utils/multi_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/utils/multi_discrete.py -------------------------------------------------------------------------------- /onpolicy/utils/separated_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/utils/separated_buffer.py -------------------------------------------------------------------------------- /onpolicy/utils/shared_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/utils/shared_buffer.py -------------------------------------------------------------------------------- /onpolicy/utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/utils/util.py -------------------------------------------------------------------------------- /onpolicy/utils/valuenorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/onpolicy/utils/valuenorm.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/marlbenchmark/on-policy/HEAD/setup.py --------------------------------------------------------------------------------