├── .gitignore ├── LICENSE ├── README.md ├── code ├── README.md ├── docs │ ├── .DS_Store │ └── overall_training_processes.png ├── experiment │ ├── .DS_Store │ └── run_different_agents_gr2.py ├── maci │ ├── __init__.py │ ├── core │ │ ├── __init__.py │ │ ├── parameterized.py │ │ └── serializable.py │ ├── distributions │ │ ├── __init__.py │ │ ├── common.py │ │ ├── gmm.py │ │ ├── normal.py │ │ ├── real_nvp_bijector.py │ │ ├── real_nvp_flow.py │ │ └── squash_bijector.py │ ├── environments │ │ ├── __init__.py │ │ ├── base_game.py │ │ ├── differential_game.py │ │ ├── discrete_static_game.py │ │ ├── env_spec.py │ │ ├── gaussian_squeeze.py │ │ ├── grid_game.py │ │ ├── gym_env.py │ │ ├── ma_env.py │ │ ├── matrix_game.py │ │ ├── multi_discrete.py │ │ ├── particle.py │ │ ├── pbeauty_game.py │ │ └── stochastic_matrix_game.py │ ├── get_agents.py │ ├── learners │ │ ├── __init__.py │ │ ├── base.py │ │ ├── maddpg.py │ │ ├── masac.py │ │ ├── masql.py │ │ ├── mavb_ac.py │ │ ├── mavb_q.py │ │ ├── sac.py │ │ └── tabular │ │ │ ├── JAL.py │ │ │ ├── MAVB.py │ │ │ ├── PHC.py │ │ │ ├── Q.py │ │ │ ├── WoLF_learner.py │ │ │ ├── __init__.py │ │ │ └── base_tabular_learner.py │ ├── misc │ │ ├── __init__.py │ │ ├── autoargs.py │ │ ├── console.py │ │ ├── kernel.py │ │ ├── logger.py │ │ ├── mlp.py │ │ ├── nn.py │ │ ├── overrides.py │ │ ├── plotter.py │ │ ├── remote_sampler.py │ │ ├── replay_pool.py │ │ ├── sampler.py │ │ ├── sga.py │ │ ├── space.py │ │ ├── tabulate.py │ │ ├── tensor_utils.py │ │ ├── tf_utils.py │ │ └── utils.py │ ├── plot.py │ ├── policies │ │ ├── __init__.py │ │ ├── base.py │ │ ├── deterministic_policy.py │ │ ├── gaussian_policy.py │ │ ├── gmm.py │ │ ├── latent_space_policy.py │ │ ├── level_k_policy.py │ │ ├── nn_policy.py │ │ ├── stochastic_policy.py │ │ └── uniform_policy.py │ ├── preprocessors │ │ ├── __init__.py │ │ └── mlp_preprocessor.py │ ├── replay_buffers │ │ ├── __init__.py │ │ ├── indexed_replay_buffer.py │ │ ├── replay_buffer.py │ │ ├── simple_replay_buffer.py │ │ └── union_buffer.py │ ├── utils.py │ └── value_functions │ │ ├── __init__.py │ │ ├── sq_value_function.py │ │ └── value_function.py ├── requirements.txt └── setup.py └── gr2_appendix.pdf /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/README.md -------------------------------------------------------------------------------- /code/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/README.md -------------------------------------------------------------------------------- /code/docs/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/docs/.DS_Store -------------------------------------------------------------------------------- /code/docs/overall_training_processes.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/docs/overall_training_processes.png -------------------------------------------------------------------------------- /code/experiment/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/experiment/.DS_Store -------------------------------------------------------------------------------- /code/experiment/run_different_agents_gr2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/experiment/run_different_agents_gr2.py -------------------------------------------------------------------------------- /code/maci/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/maci/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/core/__init__.py -------------------------------------------------------------------------------- /code/maci/core/parameterized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/core/parameterized.py -------------------------------------------------------------------------------- /code/maci/core/serializable.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/core/serializable.py -------------------------------------------------------------------------------- /code/maci/distributions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/__init__.py -------------------------------------------------------------------------------- /code/maci/distributions/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/common.py -------------------------------------------------------------------------------- /code/maci/distributions/gmm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/gmm.py -------------------------------------------------------------------------------- /code/maci/distributions/normal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/normal.py -------------------------------------------------------------------------------- /code/maci/distributions/real_nvp_bijector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/real_nvp_bijector.py -------------------------------------------------------------------------------- /code/maci/distributions/real_nvp_flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/real_nvp_flow.py -------------------------------------------------------------------------------- /code/maci/distributions/squash_bijector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/distributions/squash_bijector.py -------------------------------------------------------------------------------- /code/maci/environments/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/__init__.py -------------------------------------------------------------------------------- /code/maci/environments/base_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/base_game.py -------------------------------------------------------------------------------- /code/maci/environments/differential_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/differential_game.py -------------------------------------------------------------------------------- /code/maci/environments/discrete_static_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/discrete_static_game.py -------------------------------------------------------------------------------- /code/maci/environments/env_spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/env_spec.py -------------------------------------------------------------------------------- /code/maci/environments/gaussian_squeeze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/gaussian_squeeze.py -------------------------------------------------------------------------------- /code/maci/environments/grid_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/grid_game.py -------------------------------------------------------------------------------- /code/maci/environments/gym_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/gym_env.py -------------------------------------------------------------------------------- /code/maci/environments/ma_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/ma_env.py -------------------------------------------------------------------------------- /code/maci/environments/matrix_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/matrix_game.py -------------------------------------------------------------------------------- /code/maci/environments/multi_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/multi_discrete.py -------------------------------------------------------------------------------- /code/maci/environments/particle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/particle.py -------------------------------------------------------------------------------- /code/maci/environments/pbeauty_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/pbeauty_game.py -------------------------------------------------------------------------------- /code/maci/environments/stochastic_matrix_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/environments/stochastic_matrix_game.py -------------------------------------------------------------------------------- /code/maci/get_agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/get_agents.py -------------------------------------------------------------------------------- /code/maci/learners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/__init__.py -------------------------------------------------------------------------------- /code/maci/learners/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/base.py -------------------------------------------------------------------------------- /code/maci/learners/maddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/maddpg.py -------------------------------------------------------------------------------- /code/maci/learners/masac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/masac.py -------------------------------------------------------------------------------- /code/maci/learners/masql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/masql.py -------------------------------------------------------------------------------- /code/maci/learners/mavb_ac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/mavb_ac.py -------------------------------------------------------------------------------- /code/maci/learners/mavb_q.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/mavb_q.py -------------------------------------------------------------------------------- /code/maci/learners/sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/sac.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/JAL.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/JAL.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/MAVB.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/MAVB.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/PHC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/PHC.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/Q.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/Q.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/WoLF_learner.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/maci/learners/tabular/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/__init__.py -------------------------------------------------------------------------------- /code/maci/learners/tabular/base_tabular_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/learners/tabular/base_tabular_learner.py -------------------------------------------------------------------------------- /code/maci/misc/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /code/maci/misc/autoargs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/autoargs.py -------------------------------------------------------------------------------- /code/maci/misc/console.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/console.py -------------------------------------------------------------------------------- /code/maci/misc/kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/kernel.py -------------------------------------------------------------------------------- /code/maci/misc/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/logger.py -------------------------------------------------------------------------------- /code/maci/misc/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/mlp.py -------------------------------------------------------------------------------- /code/maci/misc/nn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/nn.py -------------------------------------------------------------------------------- /code/maci/misc/overrides.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/overrides.py -------------------------------------------------------------------------------- /code/maci/misc/plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/plotter.py -------------------------------------------------------------------------------- /code/maci/misc/remote_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/remote_sampler.py -------------------------------------------------------------------------------- /code/maci/misc/replay_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/replay_pool.py -------------------------------------------------------------------------------- /code/maci/misc/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/sampler.py -------------------------------------------------------------------------------- /code/maci/misc/sga.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/sga.py -------------------------------------------------------------------------------- /code/maci/misc/space.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/space.py -------------------------------------------------------------------------------- /code/maci/misc/tabulate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/tabulate.py -------------------------------------------------------------------------------- /code/maci/misc/tensor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/tensor_utils.py -------------------------------------------------------------------------------- /code/maci/misc/tf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/tf_utils.py -------------------------------------------------------------------------------- /code/maci/misc/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/misc/utils.py -------------------------------------------------------------------------------- /code/maci/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/plot.py -------------------------------------------------------------------------------- /code/maci/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/__init__.py -------------------------------------------------------------------------------- /code/maci/policies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/base.py -------------------------------------------------------------------------------- /code/maci/policies/deterministic_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/deterministic_policy.py -------------------------------------------------------------------------------- /code/maci/policies/gaussian_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/gaussian_policy.py -------------------------------------------------------------------------------- /code/maci/policies/gmm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/gmm.py -------------------------------------------------------------------------------- /code/maci/policies/latent_space_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/latent_space_policy.py -------------------------------------------------------------------------------- /code/maci/policies/level_k_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/level_k_policy.py -------------------------------------------------------------------------------- /code/maci/policies/nn_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/nn_policy.py -------------------------------------------------------------------------------- /code/maci/policies/stochastic_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/stochastic_policy.py -------------------------------------------------------------------------------- /code/maci/policies/uniform_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/policies/uniform_policy.py -------------------------------------------------------------------------------- /code/maci/preprocessors/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/preprocessors/__init__.py -------------------------------------------------------------------------------- /code/maci/preprocessors/mlp_preprocessor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/preprocessors/mlp_preprocessor.py -------------------------------------------------------------------------------- /code/maci/replay_buffers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/replay_buffers/__init__.py -------------------------------------------------------------------------------- /code/maci/replay_buffers/indexed_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/replay_buffers/indexed_replay_buffer.py -------------------------------------------------------------------------------- /code/maci/replay_buffers/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/replay_buffers/replay_buffer.py -------------------------------------------------------------------------------- /code/maci/replay_buffers/simple_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/replay_buffers/simple_replay_buffer.py -------------------------------------------------------------------------------- /code/maci/replay_buffers/union_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/replay_buffers/union_buffer.py -------------------------------------------------------------------------------- /code/maci/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/utils.py -------------------------------------------------------------------------------- /code/maci/value_functions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/value_functions/__init__.py -------------------------------------------------------------------------------- /code/maci/value_functions/sq_value_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/value_functions/sq_value_function.py -------------------------------------------------------------------------------- /code/maci/value_functions/value_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/maci/value_functions/value_function.py -------------------------------------------------------------------------------- /code/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/requirements.txt -------------------------------------------------------------------------------- /code/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/code/setup.py -------------------------------------------------------------------------------- /gr2_appendix.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ying-wen/gr2/HEAD/gr2_appendix.pdf --------------------------------------------------------------------------------