404
- -Page not found
- - -From 6d40ad16508b1f330b16b6f00512d9e52c25fdef Mon Sep 17 00:00:00 2001 From: Itai Caspi <30383381+itaicaspi-intel@users.noreply.github.com> Date: Thu, 15 Nov 2018 15:00:13 +0200 Subject: [PATCH] update of api docstrings across coach and tutorials [WIP] (#91) * updating the documentation website * adding the built docs * update of api docstrings across coach and tutorials 0-2 * added some missing api documentation * New Sphinx based documentation --- .gitignore | 2 + docs/404.html | 244 - .../design_imgs => _images}/ac.png | Bin docs/{img => _images}/act.png | Bin docs/_images/algorithms.png | Bin 0 -> 51160 bytes docs/_images/attention_discretization.png | Bin 0 -> 16399 bytes docs/{img => _images}/bollinger_bands.png | Bin docs/_images/box_discretization.png | Bin 0 -> 17143 bytes docs/_images/box_masking.png | Bin 0 -> 12810 bytes .../design_imgs => _images}/bs_dqn.png | Bin docs/_images/cil.png | Bin 0 -> 27469 bytes .../compare_by_num_episodes.png | Bin docs/{img => _images}/compare_by_time.png | Bin .../design_imgs => _images}/ddpg.png | Bin docs/_images/design.png | Bin 0 -> 109083 bytes .../design_imgs => _images}/dfp.png | Bin docs/{img => _images}/distributed.png | Bin .../distributional_dqn.png | Bin .../design_imgs => _images}/dqn.png | Bin .../design_imgs => _images}/dueling_dqn.png | Bin docs/{img => _images}/filters.png | Bin .../full_discrete_action_space_map.png | Bin 0 -> 20410 bytes docs/{img => _images}/improve.png | Bin docs/_images/linear_box_to_box_map.png | Bin 0 -> 12532 bytes .../design_imgs => _images}/naf.png | Bin .../design_imgs => _images}/nec.png | Bin docs/{img => _images}/network.png | Bin docs/{img => _images}/observe.png | Bin .../partial_discrete_action_space_map.png | Bin 0 -> 8562 bytes .../design_imgs => _images}/pg.png | Bin .../design_imgs => _images}/ppo.png | Bin docs/_images/qr_dqn.png | Bin 0 -> 26793 bytes docs/_images/rainbow.png | Bin 0 -> 38143 bytes docs/{img => _images}/separate_signals.png | Bin docs/{img => _images}/train.png | Bin .../{img => _images}/updating_dynamically.gif | Bin docs/_modules/index.html | 296 + .../rl_coach/agents/actor_critic_agent.html | 413 + docs/_modules/rl_coach/agents/agent.html | 1153 ++ docs/_modules/rl_coach/agents/bc_agent.html | 308 + .../agents/categorical_dqn_agent.html | 382 + docs/_modules/rl_coach/agents/cil_agent.html | 314 + .../rl_coach/agents/clipped_ppo_agent.html | 563 + docs/_modules/rl_coach/agents/ddpg_agent.html | 443 + docs/_modules/rl_coach/agents/dfp_agent.html | 475 + docs/_modules/rl_coach/agents/dqn_agent.html | 326 + docs/_modules/rl_coach/agents/mmc_agent.html | 306 + .../rl_coach/agents/n_step_q_agent.html | 373 + docs/_modules/rl_coach/agents/naf_agent.html | 354 + docs/_modules/rl_coach/agents/nec_agent.html | 435 + docs/_modules/rl_coach/agents/pal_agent.html | 334 + .../agents/policy_gradients_agent.html | 356 + docs/_modules/rl_coach/agents/ppo_agent.html | 620 + .../rl_coach/agents/qr_dqn_agent.html | 347 + .../rl_coach/agents/rainbow_dqn_agent.html | 359 + .../agents/value_optimization_agent.html | 325 + .../rl_coach/architectures/architecture.html | 442 + .../architectures/network_wrapper.html | 480 + docs/_modules/rl_coach/base_parameters.html | 801 ++ docs/_modules/rl_coach/core_types.html | 1092 ++ .../environments/carla_environment.html | 695 ++ .../control_suite_environment.html | 426 + .../environments/doom_environment.html | 495 + .../rl_coach/environments/environment.html | 721 ++ .../environments/gym_environment.html | 703 ++ .../environments/starcraft2_environment.html | 478 + .../exploration_policies/additive_noise.html | 330 + .../exploration_policies/boltzmann.html | 292 + .../exploration_policies/bootstrapped.html | 315 + .../exploration_policies/categorical.html | 281 + .../continuous_entropy.html | 265 + .../exploration_policies/e_greedy.html | 342 + .../exploration_policy.html | 311 + .../rl_coach/exploration_policies/greedy.html | 278 + .../exploration_policies/ou_process.html | 313 + .../exploration_policies/parameter_noise.html | 314 + .../truncated_normal.html | 337 + .../rl_coach/exploration_policies/ucb.html | 319 + .../action/attention_discretization.html | 300 + .../filters/action/box_discretization.html | 300 + .../rl_coach/filters/action/box_masking.html | 308 + .../full_discrete_action_space_map.html | 261 + .../filters/action/linear_box_to_box_map.html | 289 + .../partial_discrete_action_space_map.html | 286 + .../observation_clipping_filter.html | 274 + .../observation/observation_crop_filter.html | 321 + .../observation_move_axis_filter.html | 294 + .../observation_normalization_filter.html | 302 + ...on_reduction_by_sub_parts_name_filter.html | 308 + ...rvation_rescale_size_by_factor_filter.html | 300 + .../observation_rescale_to_size_filter.html | 326 + .../observation_rgb_to_y_filter.html | 278 + .../observation_squeeze_filter.html | 276 + .../observation_stacking_filter.html | 335 + .../observation_to_uint8_filter.html | 292 + .../reward/reward_clipping_filter.html | 281 + .../reward/reward_normalization_filter.html | 297 + .../filters/reward/reward_rescale_filter.html | 271 + .../episodic/episodic_experience_replay.html | 535 + .../episodic_hindsight_experience_replay.html | 375 + ...sodic_hrl_hindsight_experience_replay.html | 300 + .../episodic/single_episode_buffer.html | 260 + .../balanced_experience_replay.html | 400 + .../differentiable_neural_dictionary.html | 518 + .../non_episodic/experience_replay.html | 467 + .../prioritized_experience_replay.html | 526 + .../non_episodic/transition_collection.html | 263 + docs/_modules/rl_coach/spaces.html | 858 ++ .../components/additional_parameters.rst.txt | 18 + .../components/agents/imitation/bc.rst.txt | 29 + .../components/agents/imitation/cil.rst.txt | 36 + docs/_sources/components/agents/index.rst.txt | 43 + .../components/agents/other/dfp.rst.txt | 39 + .../agents/policy_optimization/ac.rst.txt | 40 + .../agents/policy_optimization/cppo.rst.txt | 44 + .../agents/policy_optimization/ddpg.rst.txt | 50 + .../agents/policy_optimization/hac.rst.txt | 24 + .../agents/policy_optimization/pg.rst.txt | 39 + .../agents/policy_optimization/ppo.rst.txt | 45 + .../agents/value_optimization/bs_dqn.rst.txt | 43 + .../categorical_dqn.rst.txt | 39 + .../value_optimization/double_dqn.rst.txt | 35 + .../agents/value_optimization/dqn.rst.txt | 37 + .../value_optimization/dueling_dqn.rst.txt | 27 + .../agents/value_optimization/mmc.rst.txt | 37 + .../agents/value_optimization/n_step.rst.txt | 35 + .../agents/value_optimization/naf.rst.txt | 33 + .../agents/value_optimization/nec.rst.txt | 50 + .../agents/value_optimization/pal.rst.txt | 45 + .../agents/value_optimization/qr_dqn.rst.txt | 33 + .../agents/value_optimization/rainbow.rst.txt | 51 + .../components/architectures/index.rst.txt | 27 + docs/_sources/components/core_types.rst.txt | 33 + .../components/environments/index.rst.txt | 70 + .../exploration_policies/index.rst.txt | 87 + .../_sources/components/filters/index.rst.txt | 28 + .../components/filters/input_filters.rst.txt | 67 + .../components/filters/output_filters.rst.txt | 37 + .../components/memories/index.rst.txt | 44 + docs/_sources/components/spaces.rst.txt | 64 + docs/_sources/contributing/add_agent.rst.txt | 80 + .../_sources/contributing/add_env.rst.txt | 40 +- .../_sources/dashboard.rst.txt | 95 +- .../_sources/design/control_flow.rst.txt | 58 +- .../design/horizontal_scaling.rst.txt | 0 docs/_sources/design/network.rst.txt | 56 + docs/_sources/features/algorithms.rst.txt | 10 + docs/_sources/features/benchmarks.rst.txt | 22 + docs/_sources/features/environments.rst.txt | 31 + docs/_sources/features/index.rst.txt | 10 + docs/_sources/index.rst.txt | 72 + docs/_sources/selecting_an_algorithm.rst.txt | 270 + docs/_sources/test.rst.txt | 8 + docs/_sources/usage.rst.txt | 158 + docs/_static/ajax-loader.gif | Bin 0 -> 673 bytes docs/_static/basic.css | 676 + docs/_static/comment-bright.png | Bin 0 -> 756 bytes docs/_static/comment-close.png | Bin 0 -> 829 bytes docs/_static/comment.png | Bin 0 -> 641 bytes docs/_static/css/badge_only.css | 1 + docs/_static/css/custom.css | 61 + docs/_static/css/theme.css | 6 + docs/_static/dark_logo.png | Bin 0 -> 37540 bytes docs/_static/doctools.js | 315 + docs/_static/documentation_options.js | 296 + docs/_static/down-pressed.png | Bin 0 -> 222 bytes docs/_static/down.png | Bin 0 -> 202 bytes docs/_static/file.png | Bin 0 -> 286 bytes docs/_static/fonts/Inconsolata-Bold.ttf | Bin 0 -> 109948 bytes docs/_static/fonts/Inconsolata-Regular.ttf | Bin 0 -> 96964 bytes docs/_static/fonts/Inconsolata.ttf | Bin 0 -> 63184 bytes docs/_static/fonts/Lato-Bold.ttf | Bin 0 -> 656544 bytes docs/_static/fonts/Lato-Regular.ttf | Bin 0 -> 656568 bytes docs/_static/fonts/Lato/lato-bold.eot | Bin 0 -> 256056 bytes docs/_static/fonts/Lato/lato-bold.ttf | Bin 0 -> 600856 bytes docs/_static/fonts/Lato/lato-bold.woff | Bin 0 -> 309728 bytes docs/_static/fonts/Lato/lato-bold.woff2 | Bin 0 -> 184912 bytes docs/_static/fonts/Lato/lato-bolditalic.eot | Bin 0 -> 266158 bytes docs/_static/fonts/Lato/lato-bolditalic.ttf | Bin 0 -> 622572 bytes docs/_static/fonts/Lato/lato-bolditalic.woff | Bin 0 -> 323344 bytes docs/_static/fonts/Lato/lato-bolditalic.woff2 | Bin 0 -> 193308 bytes docs/_static/fonts/Lato/lato-italic.eot | Bin 0 -> 268604 bytes docs/_static/fonts/Lato/lato-italic.ttf | Bin 0 -> 639388 bytes docs/_static/fonts/Lato/lato-italic.woff | Bin 0 -> 328412 bytes docs/_static/fonts/Lato/lato-italic.woff2 | Bin 0 -> 195704 bytes docs/_static/fonts/Lato/lato-regular.eot | Bin 0 -> 253461 bytes docs/_static/fonts/Lato/lato-regular.ttf | Bin 0 -> 607720 bytes docs/_static/fonts/Lato/lato-regular.woff | Bin 0 -> 309192 bytes docs/_static/fonts/Lato/lato-regular.woff2 | Bin 0 -> 182708 bytes docs/_static/fonts/RobotoSlab-Bold.ttf | Bin 0 -> 170616 bytes docs/_static/fonts/RobotoSlab-Regular.ttf | Bin 0 -> 169064 bytes .../fonts/RobotoSlab/roboto-slab-v7-bold.eot | Bin 0 -> 79520 bytes .../fonts/RobotoSlab/roboto-slab-v7-bold.ttf | Bin 0 -> 170616 bytes .../fonts/RobotoSlab/roboto-slab-v7-bold.woff | Bin 0 -> 87624 bytes .../RobotoSlab/roboto-slab-v7-bold.woff2 | Bin 0 -> 67312 bytes .../RobotoSlab/roboto-slab-v7-regular.eot | Bin 0 -> 78331 bytes .../RobotoSlab/roboto-slab-v7-regular.ttf | Bin 0 -> 169064 bytes .../RobotoSlab/roboto-slab-v7-regular.woff | Bin 0 -> 86288 bytes .../RobotoSlab/roboto-slab-v7-regular.woff2 | Bin 0 -> 66444 bytes docs/_static/fonts/fontawesome-webfont.eot | Bin 0 -> 165742 bytes docs/_static/fonts/fontawesome-webfont.svg | 2671 ++++ docs/_static/fonts/fontawesome-webfont.ttf | Bin 0 -> 165548 bytes docs/_static/fonts/fontawesome-webfont.woff | Bin 0 -> 98024 bytes docs/_static/fonts/fontawesome-webfont.woff2 | Bin 0 -> 77160 bytes docs/_static/jquery-3.2.1.js | 10253 ++++++++++++++++ docs/_static/jquery.js | 4 + docs/_static/js/modernizr.min.js | 4 + docs/_static/js/theme.js | 3 + docs/_static/minus.png | Bin 0 -> 90 bytes docs/_static/plus.png | Bin 0 -> 90 bytes docs/_static/pygments.css | 69 + docs/_static/searchtools.js | 482 + docs/_static/underscore-1.3.1.js | 999 ++ docs/_static/underscore.js | 31 + docs/_static/up-pressed.png | Bin 0 -> 214 bytes docs/_static/up.png | Bin 0 -> 203 bytes docs/_static/websupport.js | 808 ++ docs/algorithms/imitation/bc/index.html | 298 - docs/algorithms/other/dfp/index.html | 299 - .../policy_optimization/ac/index.html | 299 - .../policy_optimization/cppo/index.html | 309 - .../policy_optimization/ddpg/index.html | 307 - .../policy_optimization/pg/index.html | 299 - .../policy_optimization/ppo/index.html | 300 - .../value_optimization/bs_dqn/index.html | 301 - .../categorical_dqn/index.html | 310 - .../value_optimization/double_dqn/index.html | 305 - .../value_optimization/dqn/index.html | 304 - .../value_optimization/dueling_dqn/index.html | 294 - .../value_optimization/mmc/index.html | 306 - .../value_optimization/n_step/index.html | 305 - .../value_optimization/naf/index.html | 297 - .../value_optimization/nec/index.html | 304 - .../value_optimization/pal/index.html | 318 - docs/components/additional_parameters.html | 391 + docs/components/agents/imitation/bc.html | 298 + docs/components/agents/imitation/cil.html | 313 + docs/components/agents/index.html | 819 ++ docs/components/agents/other/dfp.html | 341 + .../agents/policy_optimization/ac.html | 331 + .../agents/policy_optimization/cppo.html | 354 + .../agents/policy_optimization/ddpg.html | 345 + .../agents/policy_optimization/hac.html | 249 + .../agents/policy_optimization/pg.html | 336 + .../agents/policy_optimization/ppo.html | 355 + .../agents/value_optimization/bs_dqn.html | 309 + .../value_optimization/categorical_dqn.html | 325 + .../agents/value_optimization/double_dqn.html | 298 + .../agents/value_optimization/dqn.html | 302 + .../value_optimization/dueling_dqn.html | 289 + .../agents/value_optimization/mmc.html | 309 + .../agents/value_optimization/n_step.html | 326 + .../agents/value_optimization/naf.html | 302 + .../agents/value_optimization/nec.html | 351 + .../agents/value_optimization/pal.html | 329 + .../agents/value_optimization/qr_dqn.html | 315 + .../agents/value_optimization/rainbow.html | 337 + docs/components/architectures/index.html | 793 ++ docs/components/core_types.html | 696 ++ docs/components/environments/index.html | 650 + .../exploration_policies/index.html | 663 + docs/components/filters/index.html | 266 + docs/components/filters/input_filters.html | 587 + docs/components/filters/output_filters.html | 384 + docs/components/memories/index.html | 431 + docs/components/spaces.html | 720 ++ docs/contributing/add_agent.html | 313 + docs/contributing/add_agent/index.html | 340 - docs/contributing/add_env.html | 332 + docs/contributing/add_env/index.html | 348 - docs/css/highlight.css | 124 - docs/css/theme.css | 12 - docs/css/theme_extra.css | 194 - docs/dashboard.html | 279 + docs/dashboard/index.html | 345 - docs/design/control_flow.html | 325 + docs/design/control_flow/index.html | 367 - docs/design/features/index.html | 328 - docs/design/filters/index.html | 416 - docs/design/horizontal_scaling.html | 394 + docs/design/network.html | 290 + docs/design/network/index.html | 310 - docs/diagrams.xml | 1 - docs/extra.css | 8 - docs/features/algorithms.html | 253 + docs/features/benchmarks.html | 266 + docs/features/environments.html | 277 + docs/features/index.html | 255 + docs/fonts/fontawesome-webfont.eot | Bin 37405 -> 0 bytes docs/fonts/fontawesome-webfont.svg | 399 - docs/fonts/fontawesome-webfont.ttf | Bin 79076 -> 0 bytes docs/fonts/fontawesome-webfont.woff | Bin 43572 -> 0 bytes docs/genindex.html | 937 ++ docs/img/algorithms.png | Bin 35829 -> 0 bytes docs/img/design.png | Bin 25863 -> 0 bytes docs/img/favicon.ico | Bin 1150 -> 0 bytes docs/index.html | 452 +- docs/js/highlight.pack.js | 2 - docs/js/jquery-2.1.1.min.js | 4 - docs/js/modernizr-2.8.3.min.js | 1 - docs/js/theme.js | 99 - docs/mdx_math.py | 80 - docs/objects.inv | Bin 0 -> 3257 bytes docs/search.html | 375 +- docs/search/lunr.min.js | 7 - docs/search/mustache.min.js | 1 - docs/search/require.js | 36 - docs/search/search-results-template.mustache | 4 - docs/search/search.js | 92 - docs/search/search_index.json | 704 -- docs/search/text.js | 390 - docs/searchindex.js | 1 + docs/selecting_an_algorithm.html | 492 + docs/setup.py | 42 - docs/sitemap.xml | 133 - docs/test.html | 722 ++ docs/usage.html | 370 + docs/usage/index.html | 460 - docs_raw/Makefile | 19 + docs_raw/README.md | 31 + docs_raw/README.txt | 12 - docs_raw/docs/__init__.py | 0 docs_raw/docs/algorithms/imitation/bc.md | 25 - docs_raw/docs/algorithms/other/dfp.md | 25 - .../docs/algorithms/policy_optimization/ac.md | 27 - .../algorithms/policy_optimization/cppo.md | 28 - .../algorithms/policy_optimization/ddpg.md | 32 - .../docs/algorithms/policy_optimization/pg.md | 27 - .../algorithms/policy_optimization/ppo.md | 24 - .../algorithms/value_optimization/bs_dqn.md | 30 - .../value_optimization/categorical_dqn.md | 33 - .../value_optimization/distributional_dqn.md | 33 - .../value_optimization/double_dqn.md | 28 - .../docs/algorithms/value_optimization/dqn.md | 28 - .../value_optimization/dueling_dqn.md | 21 - .../docs/algorithms/value_optimization/mmc.md | 32 - .../algorithms/value_optimization/n_step.md | 30 - .../docs/algorithms/value_optimization/naf.md | 22 - .../docs/algorithms/value_optimization/nec.md | 28 - .../docs/algorithms/value_optimization/pal.md | 32 - docs_raw/docs/contributing/add_agent.md | 68 - docs_raw/docs/design/features.md | 44 - docs_raw/docs/design/filters.md | 116 - docs_raw/docs/design/network.md | 36 - docs_raw/docs/extra.css | 8 - docs_raw/docs/img/algorithms.png | Bin 35829 -> 0 bytes docs_raw/docs/img/design.png | Bin 25863 -> 0 bytes docs_raw/docs/img/graph.png | Bin 29603 -> 0 bytes docs_raw/docs/img/level.png | Bin 24295 -> 0 bytes docs_raw/docs/index.md | 25 - docs_raw/docs/mdx_math.py | 80 - docs_raw/docs/setup.py | 42 - docs_raw/docs/usage.md | 133 - docs_raw/fix_index.py | 37 - docs_raw/make.bat | 35 + docs_raw/mkdocs.yml | 44 - {docs => docs_raw/source}/__init__.py | 0 docs_raw/source/_static/css/custom.css | 61 + docs_raw/{docs => source/_static}/img/act.png | Bin docs_raw/source/_static/img/algorithms.png | Bin 0 -> 51160 bytes .../_static/img/attention_discretization.png | Bin 0 -> 16399 bytes .../_static}/img/bollinger_bands.png | Bin .../source/_static/img/box_discretization.png | Bin 0 -> 17143 bytes docs_raw/source/_static/img/box_masking.png | Bin 0 -> 12810 bytes .../_static}/img/compare_by_num_episodes.png | Bin .../_static}/img/compare_by_time.png | Bin docs_raw/source/_static/img/dark_logo.png | Bin 0 -> 37540 bytes docs_raw/source/_static/img/design.png | Bin 0 -> 109083 bytes .../_static/img}/design_imgs/ac.png | Bin .../_static/img}/design_imgs/bs_dqn.png | Bin .../source/_static/img/design_imgs/cil.png | Bin 0 -> 27469 bytes .../_static/img}/design_imgs/ddpg.png | Bin .../_static/img}/design_imgs/dfp.png | Bin .../img}/design_imgs/distributional_dqn.png | Bin .../_static/img}/design_imgs/dqn.png | Bin .../_static/img}/design_imgs/dueling_dqn.png | Bin .../_static/img}/design_imgs/naf.png | Bin .../_static/img}/design_imgs/nec.png | Bin .../_static/img}/design_imgs/pg.png | Bin .../_static/img}/design_imgs/ppo.png | Bin .../source/_static/img/design_imgs/qr_dqn.png | Bin 0 -> 26793 bytes .../_static/img/design_imgs/rainbow.png | Bin 0 -> 38143 bytes docs_raw/source/_static/img/diagrams.xml | 1 + .../_static}/img/distributed.png | Bin .../{docs => source/_static}/img/filters.png | Bin .../img/full_discrete_action_space_map.png | Bin 0 -> 20410 bytes .../source/_static}/img/graph.png | Bin .../{docs => source/_static}/img/improve.png | Bin .../source/_static}/img/level.png | Bin .../_static/img/linear_box_to_box_map.png | Bin 0 -> 12532 bytes .../{docs => source/_static}/img/network.png | Bin .../{docs => source/_static}/img/observe.png | Bin .../source/_static/img/output_filters.xml | 1 + .../img/partial_discrete_action_space_map.png | Bin 0 -> 8562 bytes .../_static}/img/separate_signals.png | Bin .../{docs => source/_static}/img/train.png | Bin .../_static}/img/updating_dynamically.gif | Bin docs_raw/source/_templates/layout.html | 4 + .../components/additional_parameters.rst | 18 + .../source/components/agents/imitation/bc.rst | 29 + .../components/agents/imitation/cil.rst | 36 + docs_raw/source/components/agents/index.rst | 43 + .../source/components/agents/other/dfp.rst | 39 + .../agents/policy_optimization/ac.rst | 40 + .../agents/policy_optimization/cppo.rst | 44 + .../agents/policy_optimization/ddpg.rst | 50 + .../agents/policy_optimization/hac.rst | 24 + .../agents/policy_optimization/pg.rst | 39 + .../agents/policy_optimization/ppo.rst | 45 + .../agents/value_optimization/bs_dqn.rst | 43 + .../value_optimization/categorical_dqn.rst | 39 + .../agents/value_optimization/double_dqn.rst | 35 + .../agents/value_optimization/dqn.rst | 37 + .../agents/value_optimization/dueling_dqn.rst | 27 + .../agents/value_optimization/mmc.rst | 37 + .../agents/value_optimization/n_step.rst | 35 + .../agents/value_optimization/naf.rst | 33 + .../agents/value_optimization/nec.rst | 50 + .../agents/value_optimization/pal.rst | 45 + .../agents/value_optimization/qr_dqn.rst | 33 + .../agents/value_optimization/rainbow.rst | 51 + .../source/components/architectures/index.rst | 27 + docs_raw/source/components/core_types.rst | 33 + .../source/components/environments/index.rst | 70 + .../components/exploration_policies/index.rst | 87 + docs_raw/source/components/filters/index.rst | 28 + .../components/filters/input_filters.rst | 67 + .../components/filters/output_filters.rst | 37 + docs_raw/source/components/memories/index.rst | 44 + docs_raw/source/components/spaces.rst | 64 + docs_raw/source/conf.py | 214 + docs_raw/source/contributing/add_agent.rst | 80 + docs_raw/source/contributing/add_env.rst | 93 + docs_raw/source/dashboard.rst | 63 + docs_raw/source/design/control_flow.rst | 102 + docs_raw/source/design/horizontal_scaling.rst | 148 + docs_raw/source/design/network.rst | 56 + docs_raw/{docs => source}/diagrams.xml | 0 docs_raw/source/features/algorithms.rst | 10 + docs_raw/source/features/benchmarks.rst | 22 + docs_raw/source/features/environments.rst | 31 + docs_raw/source/features/index.rst | 10 + docs_raw/source/index.rst | 72 + docs_raw/source/selecting_an_algorithm.rst | 270 + docs_raw/source/test.rst | 8 + docs_raw/source/usage.rst | 158 + rl_coach/agents/actor_critic_agent.py | 18 +- rl_coach/agents/agent.py | 133 +- rl_coach/agents/bc_agent.py | 1 - rl_coach/agents/categorical_dqn_agent.py | 13 + rl_coach/agents/cil_agent.py | 5 +- rl_coach/agents/clipped_ppo_agent.py | 42 +- rl_coach/agents/ddpg_agent.py | 27 + rl_coach/agents/dfp_agent.py | 29 + rl_coach/agents/hac_ddpg_agent.py | 9 +- rl_coach/agents/mmc_agent.py | 5 + rl_coach/agents/n_step_q_agent.py | 20 + rl_coach/agents/nec_agent.py | 33 + rl_coach/agents/pal_agent.py | 13 + rl_coach/agents/policy_gradients_agent.py | 21 + rl_coach/agents/ppo_agent.py | 46 +- rl_coach/agents/qr_dqn_agent.py | 8 + rl_coach/agents/rainbow_dqn_agent.py | 11 + rl_coach/architectures/architecture.py | 22 +- rl_coach/architectures/network_wrapper.py | 17 +- .../embedders/embedder.py | 23 +- .../middlewares/middleware.py | 24 +- rl_coach/base_parameters.py | 189 +- rl_coach/coach.py | 145 +- rl_coach/core_types.py | 103 +- .../environments/control_suite_environment.py | 32 + rl_coach/environments/doom_environment.py | 30 + rl_coach/environments/environment.py | 31 +- rl_coach/environments/gym_environment.py | 37 +- rl_coach/exploration_policies/__init__.py | 40 + .../exploration_policies/additive_noise.py | 8 + rl_coach/exploration_policies/boltzmann.py | 6 + rl_coach/exploration_policies/bootstrapped.py | 11 + rl_coach/exploration_policies/categorical.py | 6 + .../continuous_entropy.py | 11 + rl_coach/exploration_policies/e_greedy.py | 13 + .../exploration_policy.py | 4 + rl_coach/exploration_policies/greedy.py | 5 + rl_coach/exploration_policies/ou_process.py | 5 + .../exploration_policies/parameter_noise.py | 10 +- .../exploration_policies/truncated_normal.py | 10 + rl_coach/exploration_policies/ucb.py | 9 + rl_coach/filters/action/__init__.py | 14 + .../action/attention_discretization.py | 13 +- rl_coach/filters/action/box_discretization.py | 9 +- rl_coach/filters/action/box_masking.py | 10 +- .../action/full_discrete_action_space_map.py | 4 +- .../filters/action/linear_box_to_box_map.py | 16 +- .../partial_discrete_action_space_map.py | 12 +- rl_coach/filters/observation/__init__.py | 25 + .../observation_clipping_filter.py | 5 +- .../observation/observation_crop_filter.py | 4 +- .../observation_move_axis_filter.py | 7 +- .../observation_normalization_filter.py | 5 +- ...tion_reduction_by_sub_parts_name_filter.py | 6 +- ...servation_rescale_size_by_factor_filter.py | 3 +- .../observation_rescale_to_size_filter.py | 3 +- .../observation_rgb_to_y_filter.py | 4 +- .../observation/observation_squeeze_filter.py | 5 +- .../observation_stacking_filter.py | 5 +- .../observation_to_uint8_filter.py | 9 +- rl_coach/filters/reward/__init__.py | 8 + .../filters/reward/reward_clipping_filter.py | 3 +- .../reward/reward_normalization_filter.py | 5 +- .../filters/reward/reward_rescale_filter.py | 3 +- rl_coach/graph_managers/graph_manager.py | 2 + rl_coach/memories/episodic/__init__.py | 14 + rl_coach/memories/non_episodic/__init__.py | 13 + rl_coach/spaces.py | 26 + tutorials/0. Quick Start Guide.ipynb | 75 +- tutorials/1. Implementing an Algorithm.ipynb | 145 +- tutorials/2. Adding an Environment.ipynb | 296 +- 517 files changed, 71034 insertions(+), 12834 deletions(-) delete mode 100644 docs/404.html rename docs/{algorithms/design_imgs => _images}/ac.png (100%) rename docs/{img => _images}/act.png (100%) create mode 100644 docs/_images/algorithms.png create mode 100644 docs/_images/attention_discretization.png rename docs/{img => _images}/bollinger_bands.png (100%) create mode 100644 docs/_images/box_discretization.png create mode 100644 docs/_images/box_masking.png rename docs/{algorithms/design_imgs => _images}/bs_dqn.png (100%) create mode 100644 docs/_images/cil.png rename docs/{img => _images}/compare_by_num_episodes.png (100%) rename docs/{img => _images}/compare_by_time.png (100%) rename docs/{algorithms/design_imgs => _images}/ddpg.png (100%) create mode 100644 docs/_images/design.png rename docs/{algorithms/design_imgs => _images}/dfp.png (100%) rename docs/{img => _images}/distributed.png (100%) rename docs/{algorithms/design_imgs => _images}/distributional_dqn.png (100%) rename docs/{algorithms/design_imgs => _images}/dqn.png (100%) rename docs/{algorithms/design_imgs => _images}/dueling_dqn.png (100%) rename docs/{img => _images}/filters.png (100%) create mode 100644 docs/_images/full_discrete_action_space_map.png rename docs/{img => _images}/improve.png (100%) create mode 100644 docs/_images/linear_box_to_box_map.png rename docs/{algorithms/design_imgs => _images}/naf.png (100%) rename docs/{algorithms/design_imgs => _images}/nec.png (100%) rename docs/{img => _images}/network.png (100%) rename docs/{img => _images}/observe.png (100%) create mode 100644 docs/_images/partial_discrete_action_space_map.png rename docs/{algorithms/design_imgs => _images}/pg.png (100%) rename docs/{algorithms/design_imgs => _images}/ppo.png (100%) create mode 100644 docs/_images/qr_dqn.png create mode 100644 docs/_images/rainbow.png rename docs/{img => _images}/separate_signals.png (100%) rename docs/{img => _images}/train.png (100%) rename docs/{img => _images}/updating_dynamically.gif (100%) create mode 100644 docs/_modules/index.html create mode 100644 docs/_modules/rl_coach/agents/actor_critic_agent.html create mode 100644 docs/_modules/rl_coach/agents/agent.html create mode 100644 docs/_modules/rl_coach/agents/bc_agent.html create mode 100644 docs/_modules/rl_coach/agents/categorical_dqn_agent.html create mode 100644 docs/_modules/rl_coach/agents/cil_agent.html create mode 100644 docs/_modules/rl_coach/agents/clipped_ppo_agent.html create mode 100644 docs/_modules/rl_coach/agents/ddpg_agent.html create mode 100644 docs/_modules/rl_coach/agents/dfp_agent.html create mode 100644 docs/_modules/rl_coach/agents/dqn_agent.html create mode 100644 docs/_modules/rl_coach/agents/mmc_agent.html create mode 100644 docs/_modules/rl_coach/agents/n_step_q_agent.html create mode 100644 docs/_modules/rl_coach/agents/naf_agent.html create mode 100644 docs/_modules/rl_coach/agents/nec_agent.html create mode 100644 docs/_modules/rl_coach/agents/pal_agent.html create mode 100644 docs/_modules/rl_coach/agents/policy_gradients_agent.html create mode 100644 docs/_modules/rl_coach/agents/ppo_agent.html create mode 100644 docs/_modules/rl_coach/agents/qr_dqn_agent.html create mode 100644 docs/_modules/rl_coach/agents/rainbow_dqn_agent.html create mode 100644 docs/_modules/rl_coach/agents/value_optimization_agent.html create mode 100644 docs/_modules/rl_coach/architectures/architecture.html create mode 100644 docs/_modules/rl_coach/architectures/network_wrapper.html create mode 100644 docs/_modules/rl_coach/base_parameters.html create mode 100644 docs/_modules/rl_coach/core_types.html create mode 100644 docs/_modules/rl_coach/environments/carla_environment.html create mode 100644 docs/_modules/rl_coach/environments/control_suite_environment.html create mode 100644 docs/_modules/rl_coach/environments/doom_environment.html create mode 100644 docs/_modules/rl_coach/environments/environment.html create mode 100644 docs/_modules/rl_coach/environments/gym_environment.html create mode 100644 docs/_modules/rl_coach/environments/starcraft2_environment.html create mode 100644 docs/_modules/rl_coach/exploration_policies/additive_noise.html create mode 100644 docs/_modules/rl_coach/exploration_policies/boltzmann.html create mode 100644 docs/_modules/rl_coach/exploration_policies/bootstrapped.html create mode 100644 docs/_modules/rl_coach/exploration_policies/categorical.html create mode 100644 docs/_modules/rl_coach/exploration_policies/continuous_entropy.html create mode 100644 docs/_modules/rl_coach/exploration_policies/e_greedy.html create mode 100644 docs/_modules/rl_coach/exploration_policies/exploration_policy.html create mode 100644 docs/_modules/rl_coach/exploration_policies/greedy.html create mode 100644 docs/_modules/rl_coach/exploration_policies/ou_process.html create mode 100644 docs/_modules/rl_coach/exploration_policies/parameter_noise.html create mode 100644 docs/_modules/rl_coach/exploration_policies/truncated_normal.html create mode 100644 docs/_modules/rl_coach/exploration_policies/ucb.html create mode 100644 docs/_modules/rl_coach/filters/action/attention_discretization.html create mode 100644 docs/_modules/rl_coach/filters/action/box_discretization.html create mode 100644 docs/_modules/rl_coach/filters/action/box_masking.html create mode 100644 docs/_modules/rl_coach/filters/action/full_discrete_action_space_map.html create mode 100644 docs/_modules/rl_coach/filters/action/linear_box_to_box_map.html create mode 100644 docs/_modules/rl_coach/filters/action/partial_discrete_action_space_map.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_clipping_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_crop_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_move_axis_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_normalization_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_reduction_by_sub_parts_name_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_rescale_size_by_factor_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_rescale_to_size_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_rgb_to_y_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_squeeze_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_stacking_filter.html create mode 100644 docs/_modules/rl_coach/filters/observation/observation_to_uint8_filter.html create mode 100644 docs/_modules/rl_coach/filters/reward/reward_clipping_filter.html create mode 100644 docs/_modules/rl_coach/filters/reward/reward_normalization_filter.html create mode 100644 docs/_modules/rl_coach/filters/reward/reward_rescale_filter.html create mode 100644 docs/_modules/rl_coach/memories/episodic/episodic_experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/episodic/episodic_hindsight_experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/episodic/episodic_hrl_hindsight_experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/episodic/single_episode_buffer.html create mode 100644 docs/_modules/rl_coach/memories/non_episodic/balanced_experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/non_episodic/differentiable_neural_dictionary.html create mode 100644 docs/_modules/rl_coach/memories/non_episodic/experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/non_episodic/prioritized_experience_replay.html create mode 100644 docs/_modules/rl_coach/memories/non_episodic/transition_collection.html create mode 100644 docs/_modules/rl_coach/spaces.html create mode 100644 docs/_sources/components/additional_parameters.rst.txt create mode 100644 docs/_sources/components/agents/imitation/bc.rst.txt create mode 100644 docs/_sources/components/agents/imitation/cil.rst.txt create mode 100644 docs/_sources/components/agents/index.rst.txt create mode 100644 docs/_sources/components/agents/other/dfp.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/ac.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/cppo.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/ddpg.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/hac.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/pg.rst.txt create mode 100644 docs/_sources/components/agents/policy_optimization/ppo.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/bs_dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/categorical_dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/double_dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/dueling_dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/mmc.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/n_step.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/naf.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/nec.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/pal.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/qr_dqn.rst.txt create mode 100644 docs/_sources/components/agents/value_optimization/rainbow.rst.txt create mode 100644 docs/_sources/components/architectures/index.rst.txt create mode 100644 docs/_sources/components/core_types.rst.txt create mode 100644 docs/_sources/components/environments/index.rst.txt create mode 100644 docs/_sources/components/exploration_policies/index.rst.txt create mode 100644 docs/_sources/components/filters/index.rst.txt create mode 100644 docs/_sources/components/filters/input_filters.rst.txt create mode 100644 docs/_sources/components/filters/output_filters.rst.txt create mode 100644 docs/_sources/components/memories/index.rst.txt create mode 100644 docs/_sources/components/spaces.rst.txt create mode 100644 docs/_sources/contributing/add_agent.rst.txt rename docs_raw/docs/contributing/add_env.md => docs/_sources/contributing/add_env.rst.txt (68%) rename docs_raw/docs/dashboard.md => docs/_sources/dashboard.rst.txt (66%) rename docs_raw/docs/design/control_flow.md => docs/_sources/design/control_flow.rst.txt (73%) rename docs_raw/docs/design/horizontal_scaling.md => docs/_sources/design/horizontal_scaling.rst.txt (100%) create mode 100644 docs/_sources/design/network.rst.txt create mode 100644 docs/_sources/features/algorithms.rst.txt create mode 100644 docs/_sources/features/benchmarks.rst.txt create mode 100644 docs/_sources/features/environments.rst.txt create mode 100644 docs/_sources/features/index.rst.txt create mode 100644 docs/_sources/index.rst.txt create mode 100644 docs/_sources/selecting_an_algorithm.rst.txt create mode 100644 docs/_sources/test.rst.txt create mode 100644 docs/_sources/usage.rst.txt create mode 100644 docs/_static/ajax-loader.gif create mode 100644 docs/_static/basic.css create mode 100644 docs/_static/comment-bright.png create mode 100644 docs/_static/comment-close.png create mode 100644 docs/_static/comment.png create mode 100644 docs/_static/css/badge_only.css create mode 100644 docs/_static/css/custom.css create mode 100644 docs/_static/css/theme.css create mode 100644 docs/_static/dark_logo.png create mode 100644 docs/_static/doctools.js create mode 100644 docs/_static/documentation_options.js create mode 100644 docs/_static/down-pressed.png create mode 100644 docs/_static/down.png create mode 100644 docs/_static/file.png create mode 100644 docs/_static/fonts/Inconsolata-Bold.ttf create mode 100644 docs/_static/fonts/Inconsolata-Regular.ttf create mode 100644 docs/_static/fonts/Inconsolata.ttf create mode 100644 docs/_static/fonts/Lato-Bold.ttf create mode 100644 docs/_static/fonts/Lato-Regular.ttf create mode 100644 docs/_static/fonts/Lato/lato-bold.eot create mode 100644 docs/_static/fonts/Lato/lato-bold.ttf create mode 100644 docs/_static/fonts/Lato/lato-bold.woff create mode 100644 docs/_static/fonts/Lato/lato-bold.woff2 create mode 100644 docs/_static/fonts/Lato/lato-bolditalic.eot create mode 100644 docs/_static/fonts/Lato/lato-bolditalic.ttf create mode 100644 docs/_static/fonts/Lato/lato-bolditalic.woff create mode 100644 docs/_static/fonts/Lato/lato-bolditalic.woff2 create mode 100644 docs/_static/fonts/Lato/lato-italic.eot create mode 100644 docs/_static/fonts/Lato/lato-italic.ttf create mode 100644 docs/_static/fonts/Lato/lato-italic.woff create mode 100644 docs/_static/fonts/Lato/lato-italic.woff2 create mode 100644 docs/_static/fonts/Lato/lato-regular.eot create mode 100644 docs/_static/fonts/Lato/lato-regular.ttf create mode 100644 docs/_static/fonts/Lato/lato-regular.woff create mode 100644 docs/_static/fonts/Lato/lato-regular.woff2 create mode 100644 docs/_static/fonts/RobotoSlab-Bold.ttf create mode 100644 docs/_static/fonts/RobotoSlab-Regular.ttf create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-bold.eot create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-bold.ttf create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-bold.woff create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-bold.woff2 create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-regular.eot create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-regular.ttf create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-regular.woff create mode 100644 docs/_static/fonts/RobotoSlab/roboto-slab-v7-regular.woff2 create mode 100644 docs/_static/fonts/fontawesome-webfont.eot create mode 100644 docs/_static/fonts/fontawesome-webfont.svg create mode 100644 docs/_static/fonts/fontawesome-webfont.ttf create mode 100644 docs/_static/fonts/fontawesome-webfont.woff create mode 100644 docs/_static/fonts/fontawesome-webfont.woff2 create mode 100644 docs/_static/jquery-3.2.1.js create mode 100644 docs/_static/jquery.js create mode 100644 docs/_static/js/modernizr.min.js create mode 100644 docs/_static/js/theme.js create mode 100644 docs/_static/minus.png create mode 100644 docs/_static/plus.png create mode 100644 docs/_static/pygments.css create mode 100644 docs/_static/searchtools.js create mode 100644 docs/_static/underscore-1.3.1.js create mode 100644 docs/_static/underscore.js create mode 100644 docs/_static/up-pressed.png create mode 100644 docs/_static/up.png create mode 100644 docs/_static/websupport.js delete mode 100644 docs/algorithms/imitation/bc/index.html delete mode 100644 docs/algorithms/other/dfp/index.html delete mode 100644 docs/algorithms/policy_optimization/ac/index.html delete mode 100644 docs/algorithms/policy_optimization/cppo/index.html delete mode 100644 docs/algorithms/policy_optimization/ddpg/index.html delete mode 100644 docs/algorithms/policy_optimization/pg/index.html delete mode 100644 docs/algorithms/policy_optimization/ppo/index.html delete mode 100644 docs/algorithms/value_optimization/bs_dqn/index.html delete mode 100644 docs/algorithms/value_optimization/categorical_dqn/index.html delete mode 100644 docs/algorithms/value_optimization/double_dqn/index.html delete mode 100644 docs/algorithms/value_optimization/dqn/index.html delete mode 100644 docs/algorithms/value_optimization/dueling_dqn/index.html delete mode 100644 docs/algorithms/value_optimization/mmc/index.html delete mode 100644 docs/algorithms/value_optimization/n_step/index.html delete mode 100644 docs/algorithms/value_optimization/naf/index.html delete mode 100644 docs/algorithms/value_optimization/nec/index.html delete mode 100644 docs/algorithms/value_optimization/pal/index.html create mode 100644 docs/components/additional_parameters.html create mode 100644 docs/components/agents/imitation/bc.html create mode 100644 docs/components/agents/imitation/cil.html create mode 100644 docs/components/agents/index.html create mode 100644 docs/components/agents/other/dfp.html create mode 100644 docs/components/agents/policy_optimization/ac.html create mode 100644 docs/components/agents/policy_optimization/cppo.html create mode 100644 docs/components/agents/policy_optimization/ddpg.html create mode 100644 docs/components/agents/policy_optimization/hac.html create mode 100644 docs/components/agents/policy_optimization/pg.html create mode 100644 docs/components/agents/policy_optimization/ppo.html create mode 100644 docs/components/agents/value_optimization/bs_dqn.html create mode 100644 docs/components/agents/value_optimization/categorical_dqn.html create mode 100644 docs/components/agents/value_optimization/double_dqn.html create mode 100644 docs/components/agents/value_optimization/dqn.html create mode 100644 docs/components/agents/value_optimization/dueling_dqn.html create mode 100644 docs/components/agents/value_optimization/mmc.html create mode 100644 docs/components/agents/value_optimization/n_step.html create mode 100644 docs/components/agents/value_optimization/naf.html create mode 100644 docs/components/agents/value_optimization/nec.html create mode 100644 docs/components/agents/value_optimization/pal.html create mode 100644 docs/components/agents/value_optimization/qr_dqn.html create mode 100644 docs/components/agents/value_optimization/rainbow.html create mode 100644 docs/components/architectures/index.html create mode 100644 docs/components/core_types.html create mode 100644 docs/components/environments/index.html create mode 100644 docs/components/exploration_policies/index.html create mode 100644 docs/components/filters/index.html create mode 100644 docs/components/filters/input_filters.html create mode 100644 docs/components/filters/output_filters.html create mode 100644 docs/components/memories/index.html create mode 100644 docs/components/spaces.html create mode 100644 docs/contributing/add_agent.html delete mode 100644 docs/contributing/add_agent/index.html create mode 100644 docs/contributing/add_env.html delete mode 100644 docs/contributing/add_env/index.html delete mode 100644 docs/css/highlight.css delete mode 100644 docs/css/theme.css delete mode 100644 docs/css/theme_extra.css create mode 100644 docs/dashboard.html delete mode 100644 docs/dashboard/index.html create mode 100644 docs/design/control_flow.html delete mode 100644 docs/design/control_flow/index.html delete mode 100644 docs/design/features/index.html delete mode 100644 docs/design/filters/index.html create mode 100644 docs/design/horizontal_scaling.html create mode 100644 docs/design/network.html delete mode 100644 docs/design/network/index.html delete mode 100644 docs/diagrams.xml delete mode 100644 docs/extra.css create mode 100644 docs/features/algorithms.html create mode 100644 docs/features/benchmarks.html create mode 100644 docs/features/environments.html create mode 100644 docs/features/index.html delete mode 100644 docs/fonts/fontawesome-webfont.eot delete mode 100644 docs/fonts/fontawesome-webfont.svg delete mode 100644 docs/fonts/fontawesome-webfont.ttf delete mode 100644 docs/fonts/fontawesome-webfont.woff create mode 100644 docs/genindex.html delete mode 100644 docs/img/algorithms.png delete mode 100644 docs/img/design.png delete mode 100644 docs/img/favicon.ico delete mode 100644 docs/js/highlight.pack.js delete mode 100644 docs/js/jquery-2.1.1.min.js delete mode 100644 docs/js/modernizr-2.8.3.min.js delete mode 100644 docs/js/theme.js delete mode 100644 docs/mdx_math.py create mode 100644 docs/objects.inv delete mode 100644 docs/search/lunr.min.js delete mode 100644 docs/search/mustache.min.js delete mode 100644 docs/search/require.js delete mode 100644 docs/search/search-results-template.mustache delete mode 100644 docs/search/search.js delete mode 100644 docs/search/search_index.json delete mode 100644 docs/search/text.js create mode 100644 docs/searchindex.js create mode 100644 docs/selecting_an_algorithm.html delete mode 100644 docs/setup.py delete mode 100644 docs/sitemap.xml create mode 100644 docs/test.html create mode 100644 docs/usage.html delete mode 100644 docs/usage/index.html create mode 100644 docs_raw/Makefile create mode 100644 docs_raw/README.md delete mode 100644 docs_raw/README.txt delete mode 100644 docs_raw/docs/__init__.py delete mode 100644 docs_raw/docs/algorithms/imitation/bc.md delete mode 100644 docs_raw/docs/algorithms/other/dfp.md delete mode 100644 docs_raw/docs/algorithms/policy_optimization/ac.md delete mode 100644 docs_raw/docs/algorithms/policy_optimization/cppo.md delete mode 100644 docs_raw/docs/algorithms/policy_optimization/ddpg.md delete mode 100644 docs_raw/docs/algorithms/policy_optimization/pg.md delete mode 100644 docs_raw/docs/algorithms/policy_optimization/ppo.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/bs_dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/categorical_dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/distributional_dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/double_dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/dueling_dqn.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/mmc.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/n_step.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/naf.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/nec.md delete mode 100644 docs_raw/docs/algorithms/value_optimization/pal.md delete mode 100644 docs_raw/docs/contributing/add_agent.md delete mode 100644 docs_raw/docs/design/features.md delete mode 100644 docs_raw/docs/design/filters.md delete mode 100644 docs_raw/docs/design/network.md delete mode 100644 docs_raw/docs/extra.css delete mode 100644 docs_raw/docs/img/algorithms.png delete mode 100644 docs_raw/docs/img/design.png delete mode 100644 docs_raw/docs/img/graph.png delete mode 100644 docs_raw/docs/img/level.png delete mode 100644 docs_raw/docs/index.md delete mode 100644 docs_raw/docs/mdx_math.py delete mode 100644 docs_raw/docs/setup.py delete mode 100644 docs_raw/docs/usage.md delete mode 100644 docs_raw/fix_index.py create mode 100644 docs_raw/make.bat delete mode 100644 docs_raw/mkdocs.yml rename {docs => docs_raw/source}/__init__.py (100%) create mode 100644 docs_raw/source/_static/css/custom.css rename docs_raw/{docs => source/_static}/img/act.png (100%) create mode 100644 docs_raw/source/_static/img/algorithms.png create mode 100644 docs_raw/source/_static/img/attention_discretization.png rename docs_raw/{docs => source/_static}/img/bollinger_bands.png (100%) create mode 100644 docs_raw/source/_static/img/box_discretization.png create mode 100644 docs_raw/source/_static/img/box_masking.png rename docs_raw/{docs => source/_static}/img/compare_by_num_episodes.png (100%) rename docs_raw/{docs => source/_static}/img/compare_by_time.png (100%) create mode 100644 docs_raw/source/_static/img/dark_logo.png create mode 100644 docs_raw/source/_static/img/design.png rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/ac.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/bs_dqn.png (100%) create mode 100644 docs_raw/source/_static/img/design_imgs/cil.png rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/ddpg.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/dfp.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/distributional_dqn.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/dqn.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/dueling_dqn.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/naf.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/nec.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/pg.png (100%) rename docs_raw/{docs/algorithms => source/_static/img}/design_imgs/ppo.png (100%) create mode 100644 docs_raw/source/_static/img/design_imgs/qr_dqn.png create mode 100644 docs_raw/source/_static/img/design_imgs/rainbow.png create mode 100644 docs_raw/source/_static/img/diagrams.xml rename docs_raw/{docs => source/_static}/img/distributed.png (100%) rename docs_raw/{docs => source/_static}/img/filters.png (100%) create mode 100644 docs_raw/source/_static/img/full_discrete_action_space_map.png rename {docs => docs_raw/source/_static}/img/graph.png (100%) rename docs_raw/{docs => source/_static}/img/improve.png (100%) rename {docs => docs_raw/source/_static}/img/level.png (100%) create mode 100644 docs_raw/source/_static/img/linear_box_to_box_map.png rename docs_raw/{docs => source/_static}/img/network.png (100%) rename docs_raw/{docs => source/_static}/img/observe.png (100%) create mode 100644 docs_raw/source/_static/img/output_filters.xml create mode 100644 docs_raw/source/_static/img/partial_discrete_action_space_map.png rename docs_raw/{docs => source/_static}/img/separate_signals.png (100%) rename docs_raw/{docs => source/_static}/img/train.png (100%) rename docs_raw/{docs => source/_static}/img/updating_dynamically.gif (100%) create mode 100644 docs_raw/source/_templates/layout.html create mode 100644 docs_raw/source/components/additional_parameters.rst create mode 100644 docs_raw/source/components/agents/imitation/bc.rst create mode 100644 docs_raw/source/components/agents/imitation/cil.rst create mode 100644 docs_raw/source/components/agents/index.rst create mode 100644 docs_raw/source/components/agents/other/dfp.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/ac.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/cppo.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/ddpg.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/hac.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/pg.rst create mode 100644 docs_raw/source/components/agents/policy_optimization/ppo.rst create mode 100644 docs_raw/source/components/agents/value_optimization/bs_dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/categorical_dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/double_dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/dueling_dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/mmc.rst create mode 100644 docs_raw/source/components/agents/value_optimization/n_step.rst create mode 100644 docs_raw/source/components/agents/value_optimization/naf.rst create mode 100644 docs_raw/source/components/agents/value_optimization/nec.rst create mode 100644 docs_raw/source/components/agents/value_optimization/pal.rst create mode 100644 docs_raw/source/components/agents/value_optimization/qr_dqn.rst create mode 100644 docs_raw/source/components/agents/value_optimization/rainbow.rst create mode 100644 docs_raw/source/components/architectures/index.rst create mode 100644 docs_raw/source/components/core_types.rst create mode 100644 docs_raw/source/components/environments/index.rst create mode 100644 docs_raw/source/components/exploration_policies/index.rst create mode 100644 docs_raw/source/components/filters/index.rst create mode 100644 docs_raw/source/components/filters/input_filters.rst create mode 100644 docs_raw/source/components/filters/output_filters.rst create mode 100644 docs_raw/source/components/memories/index.rst create mode 100644 docs_raw/source/components/spaces.rst create mode 100644 docs_raw/source/conf.py create mode 100644 docs_raw/source/contributing/add_agent.rst create mode 100644 docs_raw/source/contributing/add_env.rst create mode 100644 docs_raw/source/dashboard.rst create mode 100644 docs_raw/source/design/control_flow.rst create mode 100644 docs_raw/source/design/horizontal_scaling.rst create mode 100644 docs_raw/source/design/network.rst rename docs_raw/{docs => source}/diagrams.xml (100%) create mode 100644 docs_raw/source/features/algorithms.rst create mode 100644 docs_raw/source/features/benchmarks.rst create mode 100644 docs_raw/source/features/environments.rst create mode 100644 docs_raw/source/features/index.rst create mode 100644 docs_raw/source/index.rst create mode 100644 docs_raw/source/selecting_an_algorithm.rst create mode 100644 docs_raw/source/test.rst create mode 100644 docs_raw/source/usage.rst diff --git a/.gitignore b/.gitignore index 39eaaf1..2f46d8b 100644 --- a/.gitignore +++ b/.gitignore @@ -30,3 +30,5 @@ trace_test* *.swo .cache/ *.pyc +coachenv + diff --git a/docs/404.html b/docs/404.html deleted file mode 100644 index 0779c3a..0000000 --- a/docs/404.html +++ /dev/null @@ -1,244 +0,0 @@ - - - -
- - - - - - -Page not found
- - -89I4;HR$N<_x+rL%eN$@
z98IWU_gdJ7VKQmfpqMyG@0n wOe%9o|@|@tdkXD%8_1h*x2BH6`~MZIqw3yno;03Anl!?xskk}cpTjQoj4=C
z4Y2kOz}7?C)T-{B4^F`TJ_5tuhX$ZMk5zB}b6Vlbb6a%a_=)S<$ityF2rsLYKRq3w
zG&lFg{OV3Cp>SwkRp?fzoADWl?!JYW8IsY+KirA*6qa5{>_?7ZznoZvqj2ISu%3@i
zT)g{Z_t#vfYpm(}HD^FQ2%jwf;!L3@3Z%ryy6Tc (OvyKSdr-Y3%!Cjm3|s*qGqaDjl1pm7IYpfNk7-Q8=y0BzpbcHPb<
zNNYowT8O|yD!_0~c&%r6#rL-lB7gtrb%zY!JJb37w{ocOJ@f)htB@t7q5bw>!U2V
zwcIQ?Xg4l__xy|zIIqprtE~m+l>QvUtQEWW@ez3?;}ikR1q>Y%gcX}9WP^hocYD_1
zR4%<3i;{fRvjj!#$-8`2Ih;Siw8yn&>&6+=lj@NR`^>kI&jiJS
z+@4{j&R6bET%x8-{;&}C4x`Cu{dRxaXIdhsqsFD~0mYy3lX^?tozd>8eV&bZIdq(>
z9y3w(5p??3g-2gJdLLgOF|C&X!ta$wDt7Q3Ngi{of1s{`0A~(Sw~|0SQtN719wmgB
zb>?+e4WWlhwl7o}jkf4Xys
z`Lv`sx-!w9MsjxQpfg{KEd~VOJaEh$02X>m_+LA%_tVO&Y<@h!AHi~H2wJ=)xFytC
z5Wc6~b|PYGfR%Sx+rY(Le*pTUD?|4DNZUWRQt^Rm^<5fJ8+rx%?X%QvpOL_}K~J}2
zfZ1Eo2wXga*G_T9iov-(s6S2lZ5!v&4A$^$aFt*)vuYfnm~=o&UK$Ht>ZHtMTRV=!
z9P=%}eiW+4IxAm79CPnq=3OE_rfx7-Dtp8M%mDd^PbLWg#iy`PB@ir|A=)fq2nE*!
zXB=VR`MnFdQ}bi1--&;?Rlyd?Btld9*5UYQqd)B1@vK*P(S%o8{L!=QGEM~VkBA|%
zyG?sy6!!hh6Ja{7g1El3F;2OivEQe6m0P&14o1e~nLbO(V%KT!?3Xs>ZmKB67Jmij
zYpFZCwr*+^oH93Lp7^GS26X_rVNMK$xW0iSG9A7m@HilmcIkANxrYjLtPtq%-EsH9
z>+tz;v1De|TZt@*<{9n>WAOE4YBY9AoU{-H(lj_Z!$cq|;4ZUR6X+cIh`B1BPs7%_
zewF{C+!O{a-wk<;sC*Wd!XDKuCDeKABU+1p1v+!P%br;-5gt=F>4<9@DqSWEJDpKD
z-bTAEZSo>F_GK80Bk-^;r6gvUFWH2o!mnDV>16ppxKW)<$)bv8ZvZ*)Ws}_(Z`cro
zjnXuZt4fY9%=2l$2YJ>>l#H?Ze78QjKp)tgtE=v(;&TNv+wh24kWwKG