├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── algo ├── __init__.py ├── a2c_acktr.py ├── kfac.py └── ppo.py ├── arguments.py ├── configurations.py ├── distributions.py ├── enjoy.py ├── envs.py ├── main.py ├── model.py ├── plot_estimators.py ├── random_starts.py ├── requirements.txt ├── reward_frequencies_trained.py ├── reward_frequency.py ├── storage.py ├── tabular ├── .DS_Store ├── README.md ├── different_alpha_value_only_experiment.py ├── n_step_expected_value.py ├── n_step_expected_value_delta.py ├── plot_aggregate_info.py ├── plot_estimators.py ├── plot_value_exps.py ├── precomputed_vals.pickle ├── ring_env.py └── valueiteration │ ├── README.md │ ├── mdp_matrix.py │ ├── value_iteration_get_ring_value.py │ └── value_iteration_matrix.py ├── test_RL_difference.py ├── utils.py └── visualize.py /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/README.md -------------------------------------------------------------------------------- /algo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/algo/__init__.py -------------------------------------------------------------------------------- /algo/a2c_acktr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/algo/a2c_acktr.py -------------------------------------------------------------------------------- /algo/kfac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/algo/kfac.py -------------------------------------------------------------------------------- /algo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/algo/ppo.py -------------------------------------------------------------------------------- /arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/arguments.py -------------------------------------------------------------------------------- /configurations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/configurations.py -------------------------------------------------------------------------------- /distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/distributions.py -------------------------------------------------------------------------------- /enjoy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/enjoy.py -------------------------------------------------------------------------------- /envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/envs.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/main.py -------------------------------------------------------------------------------- /model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/model.py -------------------------------------------------------------------------------- /plot_estimators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/plot_estimators.py -------------------------------------------------------------------------------- /random_starts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/random_starts.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | gym 2 | matplotlib 3 | pybullet 4 | -------------------------------------------------------------------------------- /reward_frequencies_trained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/reward_frequencies_trained.py -------------------------------------------------------------------------------- /reward_frequency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/reward_frequency.py -------------------------------------------------------------------------------- /storage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/storage.py -------------------------------------------------------------------------------- /tabular/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/.DS_Store -------------------------------------------------------------------------------- /tabular/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/README.md -------------------------------------------------------------------------------- /tabular/different_alpha_value_only_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/different_alpha_value_only_experiment.py -------------------------------------------------------------------------------- /tabular/n_step_expected_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/n_step_expected_value.py -------------------------------------------------------------------------------- /tabular/n_step_expected_value_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/n_step_expected_value_delta.py -------------------------------------------------------------------------------- /tabular/plot_aggregate_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/plot_aggregate_info.py -------------------------------------------------------------------------------- /tabular/plot_estimators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/plot_estimators.py -------------------------------------------------------------------------------- /tabular/plot_value_exps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/plot_value_exps.py -------------------------------------------------------------------------------- /tabular/precomputed_vals.pickle: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/precomputed_vals.pickle -------------------------------------------------------------------------------- /tabular/ring_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/ring_env.py -------------------------------------------------------------------------------- /tabular/valueiteration/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/valueiteration/README.md -------------------------------------------------------------------------------- /tabular/valueiteration/mdp_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/valueiteration/mdp_matrix.py -------------------------------------------------------------------------------- /tabular/valueiteration/value_iteration_get_ring_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/valueiteration/value_iteration_get_ring_value.py -------------------------------------------------------------------------------- /tabular/valueiteration/value_iteration_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/tabular/valueiteration/value_iteration_matrix.py -------------------------------------------------------------------------------- /test_RL_difference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/test_RL_difference.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/utils.py -------------------------------------------------------------------------------- /visualize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/td-delta/HEAD/visualize.py --------------------------------------------------------------------------------