├── .gitignore ├── LICENSE ├── README.md ├── algos ├── cpo.py ├── main.py └── trpo.py ├── assets ├── expert_traj │ └── TRPO │ │ └── CartPole-v1_expert_traj_50.p └── learned_models │ ├── CPO │ └── CartPole │ │ ├── 2021-10-17-exp-1-CartPole-v1 │ │ ├── intermediate_model │ │ │ ├── model_iter_10.p │ │ │ ├── model_iter_100.p │ │ │ ├── model_iter_110.p │ │ │ ├── model_iter_120.p │ │ │ ├── model_iter_130.p │ │ │ ├── model_iter_140.p │ │ │ ├── model_iter_150.p │ │ │ ├── model_iter_160.p │ │ │ ├── model_iter_170.p │ │ │ ├── model_iter_180.p │ │ │ ├── model_iter_190.p │ │ │ ├── model_iter_20.p │ │ │ ├── model_iter_200.p │ │ │ ├── model_iter_210.p │ │ │ ├── model_iter_220.p │ │ │ ├── model_iter_230.p │ │ │ ├── model_iter_240.p │ │ │ ├── model_iter_250.p │ │ │ ├── model_iter_260.p │ │ │ ├── model_iter_270.p │ │ │ ├── model_iter_280.p │ │ │ ├── model_iter_290.p │ │ │ ├── model_iter_30.p │ │ │ ├── model_iter_300.p │ │ │ ├── model_iter_310.p │ │ │ ├── model_iter_320.p │ │ │ ├── model_iter_330.p │ │ │ ├── model_iter_340.p │ │ │ ├── model_iter_350.p │ │ │ ├── model_iter_360.p │ │ │ ├── model_iter_370.p │ │ │ ├── model_iter_380.p │ │ │ ├── model_iter_390.p │ │ │ ├── model_iter_40.p │ │ │ ├── model_iter_400.p │ │ │ ├── model_iter_410.p │ │ │ ├── model_iter_420.p │ │ │ ├── model_iter_430.p │ │ │ ├── model_iter_440.p │ │ │ ├── model_iter_450.p │ │ │ ├── model_iter_460.p │ │ │ ├── model_iter_50.p │ │ │ ├── model_iter_60.p │ │ │ ├── model_iter_70.p │ │ │ ├── model_iter_80.p │ │ │ └── model_iter_90.p │ │ ├── model.p │ │ └── runs │ │ │ ├── data_rewards_env_avg_reward │ │ │ └── events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.4 │ │ │ ├── events.out.tfevents.1634512422.ecelbw00201.engr.tamu.edu.69536.0 │ │ │ ├── events.out.tfevents.1634512451.ecelbw00201.engr.tamu.edu.69641.0 │ │ │ ├── events.out.tfevents.1634512524.ecelbw00201.engr.tamu.edu.69884.0 │ │ │ ├── events.out.tfevents.1634512587.ecelbw00201.engr.tamu.edu.70090.0 │ │ │ ├── events.out.tfevents.1634512632.ecelbw00201.engr.tamu.edu.70250.0 │ │ │ ├── events.out.tfevents.1634512721.ecelbw00201.engr.tamu.edu.70537.0 │ │ │ ├── events.out.tfevents.1634513122.ecelbw00201.engr.tamu.edu.73278.0 │ │ │ ├── events.out.tfevents.1634513237.ecelbw00201.engr.tamu.edu.73667.0 │ │ │ ├── events.out.tfevents.1634513308.ecelbw00201.engr.tamu.edu.73931.0 │ │ │ ├── events.out.tfevents.1634513350.ecelbw00201.engr.tamu.edu.74103.0 │ │ │ ├── losses_mmd_loss │ │ │ └── events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.3 │ │ │ ├── losses_p_loss │ │ │ └── events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.2 │ │ │ └── losses_v_loss │ │ │ └── events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.1 │ │ └── 2021-10-18-exp-1-CartPole-v1 │ │ ├── model.p │ │ └── runs │ │ ├── data_rewards_env_avg_reward │ │ ├── events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.4 │ │ ├── events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.4 │ │ └── events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.4 │ │ ├── events.out.tfevents.1634594502.ecelbw00201.engr.tamu.edu.14762.0 │ │ ├── events.out.tfevents.1634594528.ecelbw00201.engr.tamu.edu.14862.0 │ │ ├── events.out.tfevents.1634595762.ecelbw00201.engr.tamu.edu.20052.0 │ │ ├── events.out.tfevents.1634595793.ecelbw00201.engr.tamu.edu.20171.0 │ │ ├── events.out.tfevents.1634595821.ecelbw00201.engr.tamu.edu.20283.0 │ │ ├── events.out.tfevents.1634595855.ecelbw00201.engr.tamu.edu.20416.0 │ │ ├── events.out.tfevents.1634595892.ecelbw00201.engr.tamu.edu.20560.0 │ │ ├── events.out.tfevents.1634595989.ecelbw00201.engr.tamu.edu.20876.0 │ │ ├── events.out.tfevents.1634596019.ecelbw00201.engr.tamu.edu.20989.0 │ │ ├── events.out.tfevents.1634596077.ecelbw00201.engr.tamu.edu.21194.0 │ │ ├── events.out.tfevents.1634599571.ecelbw00201.engr.tamu.edu.34099.0 │ │ ├── events.out.tfevents.1634599654.ecelbw00201.engr.tamu.edu.35783.0 │ │ ├── events.out.tfevents.1634599700.ecelbw00201.engr.tamu.edu.35944.0 │ │ ├── events.out.tfevents.1634599736.ecelbw00201.engr.tamu.edu.36071.0 │ │ ├── events.out.tfevents.1634599796.ecelbw00201.engr.tamu.edu.36278.0 │ │ ├── events.out.tfevents.1634599837.ecelbw00201.engr.tamu.edu.36426.0 │ │ ├── events.out.tfevents.1634599869.ecelbw00201.engr.tamu.edu.36554.0 │ │ ├── events.out.tfevents.1634599918.ecelbw00201.engr.tamu.edu.36725.0 │ │ ├── events.out.tfevents.1634600146.ecelbw00201.engr.tamu.edu.37434.0 │ │ ├── events.out.tfevents.1634600188.ecelbw00201.engr.tamu.edu.37584.0 │ │ ├── events.out.tfevents.1634600214.ecelbw00201.engr.tamu.edu.37685.0 │ │ ├── events.out.tfevents.1634600235.ecelbw00201.engr.tamu.edu.37779.0 │ │ ├── events.out.tfevents.1634600305.ecelbw00201.engr.tamu.edu.38010.0 │ │ ├── events.out.tfevents.1634600451.ecelbw00201.engr.tamu.edu.38484.0 │ │ ├── events.out.tfevents.1634600533.ecelbw00201.engr.tamu.edu.38765.0 │ │ ├── events.out.tfevents.1634600717.ecelbw00201.engr.tamu.edu.39350.0 │ │ ├── events.out.tfevents.1634600756.ecelbw00201.engr.tamu.edu.39490.0 │ │ ├── events.out.tfevents.1634600790.ecelbw00201.engr.tamu.edu.39616.0 │ │ ├── events.out.tfevents.1634600823.ecelbw00201.engr.tamu.edu.39738.0 │ │ ├── events.out.tfevents.1634600867.ecelbw00201.engr.tamu.edu.39893.0 │ │ ├── events.out.tfevents.1634600964.ecelbw00201.engr.tamu.edu.40217.0 │ │ ├── events.out.tfevents.1634601000.ecelbw00201.engr.tamu.edu.40352.0 │ │ ├── events.out.tfevents.1634601041.ecelbw00201.engr.tamu.edu.40501.0 │ │ ├── events.out.tfevents.1634601080.ecelbw00201.engr.tamu.edu.40638.0 │ │ ├── events.out.tfevents.1634601139.ecelbw00201.engr.tamu.edu.40839.0 │ │ ├── events.out.tfevents.1634601288.ecelbw00201.engr.tamu.edu.41321.0 │ │ ├── events.out.tfevents.1634601335.ecelbw00201.engr.tamu.edu.41494.0 │ │ ├── events.out.tfevents.1634601417.ecelbw00201.engr.tamu.edu.41774.0 │ │ ├── events.out.tfevents.1634601452.ecelbw00201.engr.tamu.edu.42015.0 │ │ ├── events.out.tfevents.1634601821.ecelbw00201.engr.tamu.edu.45162.0 │ │ ├── losses_cost_loss │ │ ├── events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.3 │ │ ├── events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.3 │ │ └── events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.3 │ │ ├── losses_p_loss │ │ ├── events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.2 │ │ ├── events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.2 │ │ └── events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.2 │ │ └── losses_v_loss │ │ ├── events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.1 │ │ ├── events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.1 │ │ └── events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.1 │ └── trpo_expert │ └── CartPole │ └── 2021-10-17-exp-1-1-CartPole-v1 │ ├── avg_reward.p │ ├── env_avg_reward.p │ ├── eval_avg_R.p │ ├── eval_avg_R_std.p │ ├── intermediate_model │ ├── model_iter_10.p │ ├── model_iter_20.p │ ├── model_iter_30.p │ ├── model_iter_40.p │ └── model_iter_50.p │ ├── model.p │ ├── num_of_episodes.p │ ├── num_of_steps.p │ ├── p_loss_list.p │ ├── rewards_std.p │ ├── runs │ ├── data_rewards_avg_reward │ │ └── events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.4 │ ├── data_rewards_env_avg_reward │ │ ├── events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.5 │ │ ├── events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.4 │ │ └── events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.4 │ ├── events.out.tfevents.1634507516.ecelbw00201.engr.tamu.edu.45909.0 │ ├── events.out.tfevents.1634507573.ecelbw00201.engr.tamu.edu.46102.0 │ ├── events.out.tfevents.1634507600.ecelbw00201.engr.tamu.edu.46198.0 │ ├── events.out.tfevents.1634507696.ecelbw00201.engr.tamu.edu.46510.0 │ ├── events.out.tfevents.1634507753.ecelbw00201.engr.tamu.edu.46725.0 │ ├── events.out.tfevents.1634508866.ecelbw00201.engr.tamu.edu.52613.0 │ ├── events.out.tfevents.1634508900.ecelbw00201.engr.tamu.edu.52733.0 │ ├── events.out.tfevents.1634509000.ecelbw00201.engr.tamu.edu.53058.0 │ ├── events.out.tfevents.1634509094.ecelbw00201.engr.tamu.edu.53372.0 │ ├── events.out.tfevents.1634509139.ecelbw00201.engr.tamu.edu.53577.0 │ ├── losses_mmd_loss │ │ ├── events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.3 │ │ ├── events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.3 │ │ └── events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.3 │ ├── losses_p_loss │ │ ├── events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.2 │ │ ├── events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.2 │ │ └── events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.2 │ └── losses_v_loss │ │ ├── events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.1 │ │ ├── events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.1 │ │ └── events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.1 │ ├── total_num_of_episodes.p │ ├── total_num_of_steps.p │ └── true_v_loss_list.p ├── core ├── agent.py ├── common.py └── save_expert_traj.py ├── cpo_theory ├── feasible.png ├── infeasible.png └── main.png ├── models ├── continuous_policy.py ├── critic.py └── discrete_policy.py └── utils ├── __init__.py ├── argument_parsing.py ├── math.py ├── model_saving.py ├── replay_memory.py ├── tools.py ├── torch.py └── zfilter.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/README.md -------------------------------------------------------------------------------- /algos/cpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/algos/cpo.py -------------------------------------------------------------------------------- /algos/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/algos/main.py -------------------------------------------------------------------------------- /algos/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/algos/trpo.py -------------------------------------------------------------------------------- /assets/expert_traj/TRPO/CartPole-v1_expert_traj_50.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/expert_traj/TRPO/CartPole-v1_expert_traj_50.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_10.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_10.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_100.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_100.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_110.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_110.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_120.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_120.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_130.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_130.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_140.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_140.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_150.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_150.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_160.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_160.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_170.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_170.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_180.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_180.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_190.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_190.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_20.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_20.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_200.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_200.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_210.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_210.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_220.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_220.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_230.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_230.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_240.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_240.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_250.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_250.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_260.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_260.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_270.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_270.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_280.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_280.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_290.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_290.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_30.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_30.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_300.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_300.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_310.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_310.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_320.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_320.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_330.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_330.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_340.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_340.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_350.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_350.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_360.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_360.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_370.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_370.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_380.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_380.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_390.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_390.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_40.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_40.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_400.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_400.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_410.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_410.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_420.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_420.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_430.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_430.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_440.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_440.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_450.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_450.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_460.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_460.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_50.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_50.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_60.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_60.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_70.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_70.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_80.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_80.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_90.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/intermediate_model/model_iter_90.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/model.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/model.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.4 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512422.ecelbw00201.engr.tamu.edu.69536.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512422.ecelbw00201.engr.tamu.edu.69536.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512451.ecelbw00201.engr.tamu.edu.69641.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512451.ecelbw00201.engr.tamu.edu.69641.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512524.ecelbw00201.engr.tamu.edu.69884.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512524.ecelbw00201.engr.tamu.edu.69884.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512587.ecelbw00201.engr.tamu.edu.70090.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512587.ecelbw00201.engr.tamu.edu.70090.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512632.ecelbw00201.engr.tamu.edu.70250.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512632.ecelbw00201.engr.tamu.edu.70250.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512721.ecelbw00201.engr.tamu.edu.70537.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634512721.ecelbw00201.engr.tamu.edu.70537.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513122.ecelbw00201.engr.tamu.edu.73278.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513122.ecelbw00201.engr.tamu.edu.73278.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513237.ecelbw00201.engr.tamu.edu.73667.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513237.ecelbw00201.engr.tamu.edu.73667.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513308.ecelbw00201.engr.tamu.edu.73931.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513308.ecelbw00201.engr.tamu.edu.73931.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513350.ecelbw00201.engr.tamu.edu.74103.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/events.out.tfevents.1634513350.ecelbw00201.engr.tamu.edu.74103.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.3 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.2 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-17-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634513361.ecelbw00201.engr.tamu.edu.74103.1 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/model.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/model.p -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.4 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.4 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.4 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634594502.ecelbw00201.engr.tamu.edu.14762.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634594502.ecelbw00201.engr.tamu.edu.14762.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634594528.ecelbw00201.engr.tamu.edu.14862.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634594528.ecelbw00201.engr.tamu.edu.14862.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595762.ecelbw00201.engr.tamu.edu.20052.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595762.ecelbw00201.engr.tamu.edu.20052.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595793.ecelbw00201.engr.tamu.edu.20171.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595793.ecelbw00201.engr.tamu.edu.20171.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595821.ecelbw00201.engr.tamu.edu.20283.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595821.ecelbw00201.engr.tamu.edu.20283.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595855.ecelbw00201.engr.tamu.edu.20416.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595855.ecelbw00201.engr.tamu.edu.20416.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595892.ecelbw00201.engr.tamu.edu.20560.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595892.ecelbw00201.engr.tamu.edu.20560.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595989.ecelbw00201.engr.tamu.edu.20876.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634595989.ecelbw00201.engr.tamu.edu.20876.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634596019.ecelbw00201.engr.tamu.edu.20989.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634596019.ecelbw00201.engr.tamu.edu.20989.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634596077.ecelbw00201.engr.tamu.edu.21194.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634596077.ecelbw00201.engr.tamu.edu.21194.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599571.ecelbw00201.engr.tamu.edu.34099.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599571.ecelbw00201.engr.tamu.edu.34099.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599654.ecelbw00201.engr.tamu.edu.35783.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599654.ecelbw00201.engr.tamu.edu.35783.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599700.ecelbw00201.engr.tamu.edu.35944.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599700.ecelbw00201.engr.tamu.edu.35944.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599736.ecelbw00201.engr.tamu.edu.36071.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599736.ecelbw00201.engr.tamu.edu.36071.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599796.ecelbw00201.engr.tamu.edu.36278.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599796.ecelbw00201.engr.tamu.edu.36278.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599837.ecelbw00201.engr.tamu.edu.36426.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599837.ecelbw00201.engr.tamu.edu.36426.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599869.ecelbw00201.engr.tamu.edu.36554.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599869.ecelbw00201.engr.tamu.edu.36554.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599918.ecelbw00201.engr.tamu.edu.36725.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634599918.ecelbw00201.engr.tamu.edu.36725.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600146.ecelbw00201.engr.tamu.edu.37434.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600146.ecelbw00201.engr.tamu.edu.37434.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600188.ecelbw00201.engr.tamu.edu.37584.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600188.ecelbw00201.engr.tamu.edu.37584.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600214.ecelbw00201.engr.tamu.edu.37685.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600214.ecelbw00201.engr.tamu.edu.37685.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600235.ecelbw00201.engr.tamu.edu.37779.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600235.ecelbw00201.engr.tamu.edu.37779.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600305.ecelbw00201.engr.tamu.edu.38010.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600305.ecelbw00201.engr.tamu.edu.38010.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600451.ecelbw00201.engr.tamu.edu.38484.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600451.ecelbw00201.engr.tamu.edu.38484.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600533.ecelbw00201.engr.tamu.edu.38765.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600533.ecelbw00201.engr.tamu.edu.38765.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600717.ecelbw00201.engr.tamu.edu.39350.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600717.ecelbw00201.engr.tamu.edu.39350.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600756.ecelbw00201.engr.tamu.edu.39490.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600756.ecelbw00201.engr.tamu.edu.39490.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600790.ecelbw00201.engr.tamu.edu.39616.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600790.ecelbw00201.engr.tamu.edu.39616.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600823.ecelbw00201.engr.tamu.edu.39738.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600823.ecelbw00201.engr.tamu.edu.39738.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600867.ecelbw00201.engr.tamu.edu.39893.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600867.ecelbw00201.engr.tamu.edu.39893.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600964.ecelbw00201.engr.tamu.edu.40217.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634600964.ecelbw00201.engr.tamu.edu.40217.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601000.ecelbw00201.engr.tamu.edu.40352.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601000.ecelbw00201.engr.tamu.edu.40352.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601041.ecelbw00201.engr.tamu.edu.40501.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601041.ecelbw00201.engr.tamu.edu.40501.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601080.ecelbw00201.engr.tamu.edu.40638.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601080.ecelbw00201.engr.tamu.edu.40638.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601139.ecelbw00201.engr.tamu.edu.40839.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601139.ecelbw00201.engr.tamu.edu.40839.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601288.ecelbw00201.engr.tamu.edu.41321.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601288.ecelbw00201.engr.tamu.edu.41321.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601335.ecelbw00201.engr.tamu.edu.41494.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601335.ecelbw00201.engr.tamu.edu.41494.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601417.ecelbw00201.engr.tamu.edu.41774.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601417.ecelbw00201.engr.tamu.edu.41774.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601452.ecelbw00201.engr.tamu.edu.42015.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601452.ecelbw00201.engr.tamu.edu.42015.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601821.ecelbw00201.engr.tamu.edu.45162.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/events.out.tfevents.1634601821.ecelbw00201.engr.tamu.edu.45162.0 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.3 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.3 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_cost_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.3 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.2 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.2 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.2 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634596084.ecelbw00201.engr.tamu.edu.21194.1 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634601454.ecelbw00201.engr.tamu.edu.42015.1 -------------------------------------------------------------------------------- /assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/CPO/CartPole/2021-10-18-exp-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634601827.ecelbw00201.engr.tamu.edu.45162.1 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/avg_reward.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/avg_reward.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/env_avg_reward.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/env_avg_reward.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/eval_avg_R.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/eval_avg_R.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/eval_avg_R_std.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/eval_avg_R_std.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_10.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_10.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_20.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_20.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_30.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_30.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_40.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_40.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_50.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/intermediate_model/model_iter_50.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/model.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/model.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/num_of_episodes.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/num_of_episodes.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/num_of_steps.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/num_of_steps.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/p_loss_list.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/p_loss_list.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/rewards_std.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/rewards_std.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_avg_reward/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_avg_reward/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.4 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.5 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.4 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/data_rewards_env_avg_reward/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.4 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507516.ecelbw00201.engr.tamu.edu.45909.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507516.ecelbw00201.engr.tamu.edu.45909.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507573.ecelbw00201.engr.tamu.edu.46102.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507573.ecelbw00201.engr.tamu.edu.46102.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507600.ecelbw00201.engr.tamu.edu.46198.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507600.ecelbw00201.engr.tamu.edu.46198.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507696.ecelbw00201.engr.tamu.edu.46510.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507696.ecelbw00201.engr.tamu.edu.46510.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507753.ecelbw00201.engr.tamu.edu.46725.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634507753.ecelbw00201.engr.tamu.edu.46725.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634508866.ecelbw00201.engr.tamu.edu.52613.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634508866.ecelbw00201.engr.tamu.edu.52613.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634508900.ecelbw00201.engr.tamu.edu.52733.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634508900.ecelbw00201.engr.tamu.edu.52733.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509000.ecelbw00201.engr.tamu.edu.53058.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509000.ecelbw00201.engr.tamu.edu.53058.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509094.ecelbw00201.engr.tamu.edu.53372.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509094.ecelbw00201.engr.tamu.edu.53372.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509139.ecelbw00201.engr.tamu.edu.53577.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/events.out.tfevents.1634509139.ecelbw00201.engr.tamu.edu.53577.0 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.3 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.3 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_mmd_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.3 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.2 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.2 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_p_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.2 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634507767.ecelbw00201.engr.tamu.edu.46725.1 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634509109.ecelbw00201.engr.tamu.edu.53372.1 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/runs/losses_v_loss/events.out.tfevents.1634509153.ecelbw00201.engr.tamu.edu.53577.1 -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/total_num_of_episodes.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/total_num_of_episodes.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/total_num_of_steps.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/total_num_of_steps.p -------------------------------------------------------------------------------- /assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/true_v_loss_list.p: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/assets/learned_models/trpo_expert/CartPole/2021-10-17-exp-1-1-CartPole-v1/true_v_loss_list.p -------------------------------------------------------------------------------- /core/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/core/agent.py -------------------------------------------------------------------------------- /core/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/core/common.py -------------------------------------------------------------------------------- /core/save_expert_traj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/core/save_expert_traj.py -------------------------------------------------------------------------------- /cpo_theory/feasible.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/cpo_theory/feasible.png -------------------------------------------------------------------------------- /cpo_theory/infeasible.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/cpo_theory/infeasible.png -------------------------------------------------------------------------------- /cpo_theory/main.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/cpo_theory/main.png -------------------------------------------------------------------------------- /models/continuous_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/models/continuous_policy.py -------------------------------------------------------------------------------- /models/critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/models/critic.py -------------------------------------------------------------------------------- /models/discrete_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/models/discrete_policy.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/__init__.py -------------------------------------------------------------------------------- /utils/argument_parsing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/argument_parsing.py -------------------------------------------------------------------------------- /utils/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/math.py -------------------------------------------------------------------------------- /utils/model_saving.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/model_saving.py -------------------------------------------------------------------------------- /utils/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/replay_memory.py -------------------------------------------------------------------------------- /utils/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/tools.py -------------------------------------------------------------------------------- /utils/torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/torch.py -------------------------------------------------------------------------------- /utils/zfilter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SapanaChaudhary/PyTorch-CPO/HEAD/utils/zfilter.py --------------------------------------------------------------------------------