├── .gitignore ├── .gitmodules ├── LICENSE ├── POMDP ├── .ipynb_checkpoints │ └── plot-checkpoint.ipynb ├── common │ ├── __pycache__ │ │ ├── buffers.cpython-36.pyc │ │ ├── initialize.cpython-36.pyc │ │ ├── policy_networks.cpython-36.pyc │ │ ├── utils.cpython-36.pyc │ │ └── value_networks.cpython-36.pyc │ ├── buffers.py │ ├── initialize.py │ ├── optimizers.py │ ├── policy_networks.py │ ├── utils.py │ └── value_networks.py ├── copy │ ├── plot.ipynb │ └── reward_compare_td3.pdf ├── plot.ipynb ├── reward_compare_sac.pdf ├── reward_compare_td3.pdf ├── sac_v2.py ├── sac_v2_lstm.py ├── td3.py └── td3_lstm.py ├── README.md ├── SDT ├── SDT.py ├── __pycache__ │ ├── SDT.cpython-36.pyc │ └── sdt_train.cpython-36.pyc └── sdt_train.py ├── ac.py ├── cem ├── .ipynb_checkpoints │ ├── CEM_Categorical_test-checkpoint.ipynb │ └── CEM_Gaussian_test-checkpoint.ipynb ├── CEM_Categorical_test.ipynb ├── CEM_Gaussian_test.ipynb ├── RunJupyter.py ├── _policies.py └── cem.py ├── common ├── __pycache__ │ ├── buffers.cpython-36.pyc │ ├── initialize.cpython-36.pyc │ ├── policy_networks.cpython-36.pyc │ ├── utils.cpython-36.pyc │ └── value_networks.cpython-36.pyc ├── buffers.py ├── initialize.py ├── optimizers.py ├── policy_networks.py ├── utils.py ├── value_networks.py └── wrappers.py ├── ddpg.py ├── ddpg_v2.py ├── dqn.py ├── dqn_multistep.py ├── img ├── ac.png ├── ac_cartpole.png ├── drl_book.png ├── mp.png ├── mp_share.png ├── pendulum.png ├── pmoe.png ├── ppo_multi.png ├── ppo_single_2 (copy).png ├── ppo_single_2.png ├── reward_compare.pdf ├── sac_autoentropy.png ├── sac_nonautoentropy.png ├── td3_deterministic.png └── td3_nondeterministic.png ├── log └── events.out.tfevents.1577364245.quantumiracle-G3-3579 ├── model ├── ddpg_policy ├── ddpg_q ├── ddpg_target_q ├── rdpg_policy ├── rdpg_q └── rdpg_target_q ├── plot.ipynb ├── plot2.ipynb ├── pmoe_ppo.py ├── pmoe_sac.py ├── ppo_continous_discrete.py ├── ppo_continuous.py ├── ppo_continuous2.py ├── ppo_continuous3.py ├── ppo_continuous_multiprocess.py ├── ppo_continuous_multiprocess2.py ├── ppo_continuous_tf.py ├── ppo_discrete.py ├── ppo_gae_continuous.py ├── ppo_gae_continuous2.py ├── ppo_gae_continuous3.py ├── ppo_gae_discrete.py ├── ppo_model ├── checkpoint ├── ppo.data-00000-of-00001 ├── ppo.index └── ppo.meta ├── ppo_multi.png ├── qlearning_sarsa_mc.ipynb ├── qmix.py ├── qt_opt_v3.py ├── ramble_sac.md ├── rdpg.py ├── reacher.py ├── reacher.pyc ├── requirements.txt ├── sac.py ├── sac_discrete.py ├── sac_discrete_per.py ├── sac_pendulum.py ├── sac_v2.py ├── sac_v2_gru.py ├── sac_v2_lstm.py ├── sac_v2_multiprocess.py ├── sac_v2_multiprocess_multi_gpu.py ├── sac_v2_multithread.py ├── sdt_ppo_gae_discrete.py ├── td3.py ├── td3_lstm.py └── td3_multiprocess.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/.gitmodules -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/LICENSE -------------------------------------------------------------------------------- /POMDP/.ipynb_checkpoints/plot-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/.ipynb_checkpoints/plot-checkpoint.ipynb -------------------------------------------------------------------------------- /POMDP/common/__pycache__/buffers.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/__pycache__/buffers.cpython-36.pyc -------------------------------------------------------------------------------- /POMDP/common/__pycache__/initialize.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/__pycache__/initialize.cpython-36.pyc -------------------------------------------------------------------------------- /POMDP/common/__pycache__/policy_networks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/__pycache__/policy_networks.cpython-36.pyc -------------------------------------------------------------------------------- /POMDP/common/__pycache__/utils.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/__pycache__/utils.cpython-36.pyc -------------------------------------------------------------------------------- /POMDP/common/__pycache__/value_networks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/__pycache__/value_networks.cpython-36.pyc -------------------------------------------------------------------------------- /POMDP/common/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/buffers.py -------------------------------------------------------------------------------- /POMDP/common/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/initialize.py -------------------------------------------------------------------------------- /POMDP/common/optimizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/optimizers.py -------------------------------------------------------------------------------- /POMDP/common/policy_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/policy_networks.py -------------------------------------------------------------------------------- /POMDP/common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/utils.py -------------------------------------------------------------------------------- /POMDP/common/value_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/common/value_networks.py -------------------------------------------------------------------------------- /POMDP/copy/plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/copy/plot.ipynb -------------------------------------------------------------------------------- /POMDP/copy/reward_compare_td3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/copy/reward_compare_td3.pdf -------------------------------------------------------------------------------- /POMDP/plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/plot.ipynb -------------------------------------------------------------------------------- /POMDP/reward_compare_sac.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/reward_compare_sac.pdf -------------------------------------------------------------------------------- /POMDP/reward_compare_td3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/reward_compare_td3.pdf -------------------------------------------------------------------------------- /POMDP/sac_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/sac_v2.py -------------------------------------------------------------------------------- /POMDP/sac_v2_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/sac_v2_lstm.py -------------------------------------------------------------------------------- /POMDP/td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/td3.py -------------------------------------------------------------------------------- /POMDP/td3_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/POMDP/td3_lstm.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/README.md -------------------------------------------------------------------------------- /SDT/SDT.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/SDT/SDT.py -------------------------------------------------------------------------------- /SDT/__pycache__/SDT.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/SDT/__pycache__/SDT.cpython-36.pyc -------------------------------------------------------------------------------- /SDT/__pycache__/sdt_train.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/SDT/__pycache__/sdt_train.cpython-36.pyc -------------------------------------------------------------------------------- /SDT/sdt_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/SDT/sdt_train.py -------------------------------------------------------------------------------- /ac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ac.py -------------------------------------------------------------------------------- /cem/.ipynb_checkpoints/CEM_Categorical_test-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/.ipynb_checkpoints/CEM_Categorical_test-checkpoint.ipynb -------------------------------------------------------------------------------- /cem/.ipynb_checkpoints/CEM_Gaussian_test-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/.ipynb_checkpoints/CEM_Gaussian_test-checkpoint.ipynb -------------------------------------------------------------------------------- /cem/CEM_Categorical_test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/CEM_Categorical_test.ipynb -------------------------------------------------------------------------------- /cem/CEM_Gaussian_test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/CEM_Gaussian_test.ipynb -------------------------------------------------------------------------------- /cem/RunJupyter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/RunJupyter.py -------------------------------------------------------------------------------- /cem/_policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/_policies.py -------------------------------------------------------------------------------- /cem/cem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/cem/cem.py -------------------------------------------------------------------------------- /common/__pycache__/buffers.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/__pycache__/buffers.cpython-36.pyc -------------------------------------------------------------------------------- /common/__pycache__/initialize.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/__pycache__/initialize.cpython-36.pyc -------------------------------------------------------------------------------- /common/__pycache__/policy_networks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/__pycache__/policy_networks.cpython-36.pyc -------------------------------------------------------------------------------- /common/__pycache__/utils.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/__pycache__/utils.cpython-36.pyc -------------------------------------------------------------------------------- /common/__pycache__/value_networks.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/__pycache__/value_networks.cpython-36.pyc -------------------------------------------------------------------------------- /common/buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/buffers.py -------------------------------------------------------------------------------- /common/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/initialize.py -------------------------------------------------------------------------------- /common/optimizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/optimizers.py -------------------------------------------------------------------------------- /common/policy_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/policy_networks.py -------------------------------------------------------------------------------- /common/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/utils.py -------------------------------------------------------------------------------- /common/value_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/value_networks.py -------------------------------------------------------------------------------- /common/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/common/wrappers.py -------------------------------------------------------------------------------- /ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ddpg.py -------------------------------------------------------------------------------- /ddpg_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ddpg_v2.py -------------------------------------------------------------------------------- /dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/dqn.py -------------------------------------------------------------------------------- /dqn_multistep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/dqn_multistep.py -------------------------------------------------------------------------------- /img/ac.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/ac.png -------------------------------------------------------------------------------- /img/ac_cartpole.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/ac_cartpole.png -------------------------------------------------------------------------------- /img/drl_book.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/drl_book.png -------------------------------------------------------------------------------- /img/mp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/mp.png -------------------------------------------------------------------------------- /img/mp_share.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/mp_share.png -------------------------------------------------------------------------------- /img/pendulum.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/pendulum.png -------------------------------------------------------------------------------- /img/pmoe.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/pmoe.png -------------------------------------------------------------------------------- /img/ppo_multi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/ppo_multi.png -------------------------------------------------------------------------------- /img/ppo_single_2 (copy).png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/ppo_single_2 (copy).png -------------------------------------------------------------------------------- /img/ppo_single_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/ppo_single_2.png -------------------------------------------------------------------------------- /img/reward_compare.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/reward_compare.pdf -------------------------------------------------------------------------------- /img/sac_autoentropy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/sac_autoentropy.png -------------------------------------------------------------------------------- /img/sac_nonautoentropy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/sac_nonautoentropy.png -------------------------------------------------------------------------------- /img/td3_deterministic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/td3_deterministic.png -------------------------------------------------------------------------------- /img/td3_nondeterministic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/img/td3_nondeterministic.png -------------------------------------------------------------------------------- /log/events.out.tfevents.1577364245.quantumiracle-G3-3579: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/log/events.out.tfevents.1577364245.quantumiracle-G3-3579 -------------------------------------------------------------------------------- /model/ddpg_policy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/ddpg_policy -------------------------------------------------------------------------------- /model/ddpg_q: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/ddpg_q -------------------------------------------------------------------------------- /model/ddpg_target_q: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/ddpg_target_q -------------------------------------------------------------------------------- /model/rdpg_policy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/rdpg_policy -------------------------------------------------------------------------------- /model/rdpg_q: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/rdpg_q -------------------------------------------------------------------------------- /model/rdpg_target_q: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/model/rdpg_target_q -------------------------------------------------------------------------------- /plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/plot.ipynb -------------------------------------------------------------------------------- /plot2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/plot2.ipynb -------------------------------------------------------------------------------- /pmoe_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/pmoe_ppo.py -------------------------------------------------------------------------------- /pmoe_sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/pmoe_sac.py -------------------------------------------------------------------------------- /ppo_continous_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continous_discrete.py -------------------------------------------------------------------------------- /ppo_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous.py -------------------------------------------------------------------------------- /ppo_continuous2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous2.py -------------------------------------------------------------------------------- /ppo_continuous3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous3.py -------------------------------------------------------------------------------- /ppo_continuous_multiprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous_multiprocess.py -------------------------------------------------------------------------------- /ppo_continuous_multiprocess2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous_multiprocess2.py -------------------------------------------------------------------------------- /ppo_continuous_tf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_continuous_tf.py -------------------------------------------------------------------------------- /ppo_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_discrete.py -------------------------------------------------------------------------------- /ppo_gae_continuous.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_gae_continuous.py -------------------------------------------------------------------------------- /ppo_gae_continuous2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_gae_continuous2.py -------------------------------------------------------------------------------- /ppo_gae_continuous3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_gae_continuous3.py -------------------------------------------------------------------------------- /ppo_gae_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_gae_discrete.py -------------------------------------------------------------------------------- /ppo_model/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_model/checkpoint -------------------------------------------------------------------------------- /ppo_model/ppo.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_model/ppo.data-00000-of-00001 -------------------------------------------------------------------------------- /ppo_model/ppo.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_model/ppo.index -------------------------------------------------------------------------------- /ppo_model/ppo.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_model/ppo.meta -------------------------------------------------------------------------------- /ppo_multi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ppo_multi.png -------------------------------------------------------------------------------- /qlearning_sarsa_mc.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/qlearning_sarsa_mc.ipynb -------------------------------------------------------------------------------- /qmix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/qmix.py -------------------------------------------------------------------------------- /qt_opt_v3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/qt_opt_v3.py -------------------------------------------------------------------------------- /ramble_sac.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/ramble_sac.md -------------------------------------------------------------------------------- /rdpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/rdpg.py -------------------------------------------------------------------------------- /reacher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/reacher.py -------------------------------------------------------------------------------- /reacher.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/reacher.pyc -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/requirements.txt -------------------------------------------------------------------------------- /sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac.py -------------------------------------------------------------------------------- /sac_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_discrete.py -------------------------------------------------------------------------------- /sac_discrete_per.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_discrete_per.py -------------------------------------------------------------------------------- /sac_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_pendulum.py -------------------------------------------------------------------------------- /sac_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2.py -------------------------------------------------------------------------------- /sac_v2_gru.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2_gru.py -------------------------------------------------------------------------------- /sac_v2_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2_lstm.py -------------------------------------------------------------------------------- /sac_v2_multiprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2_multiprocess.py -------------------------------------------------------------------------------- /sac_v2_multiprocess_multi_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2_multiprocess_multi_gpu.py -------------------------------------------------------------------------------- /sac_v2_multithread.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sac_v2_multithread.py -------------------------------------------------------------------------------- /sdt_ppo_gae_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/sdt_ppo_gae_discrete.py -------------------------------------------------------------------------------- /td3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/td3.py -------------------------------------------------------------------------------- /td3_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/td3_lstm.py -------------------------------------------------------------------------------- /td3_multiprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/quantumiracle/Popular-RL-Algorithms/HEAD/td3_multiprocess.py --------------------------------------------------------------------------------