agilerl 2.4.1.dev3__tar.gz → 2.4.2.dev0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (352) hide show
  1. agilerl-2.4.2.dev0/.coveragerc +9 -0
  2. agilerl-2.4.2.dev0/.github/ISSUE_TEMPLATE/bug_report.md +27 -0
  3. agilerl-2.4.2.dev0/.github/ISSUE_TEMPLATE/feature_request.md +20 -0
  4. agilerl-2.4.2.dev0/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md +34 -0
  5. agilerl-2.4.2.dev0/.github/badges/arena-github-badge.svg +24 -0
  6. agilerl-2.4.2.dev0/.github/workflows/codeql.yml +101 -0
  7. agilerl-2.4.2.dev0/.github/workflows/python-app.yml +59 -0
  8. agilerl-2.4.2.dev0/.gitignore +145 -0
  9. agilerl-2.4.2.dev0/.pre-commit-config.yaml +58 -0
  10. agilerl-2.4.2.dev0/.readthedocs.yaml +30 -0
  11. agilerl-2.4.2.dev0/CITATION.cff +20 -0
  12. agilerl-2.4.2.dev0/CODE_OF_CONDUCT.md +128 -0
  13. agilerl-2.4.2.dev0/CONTRIBUTING.md +73 -0
  14. agilerl-2.4.2.dev0/DQN_LEARNING_ALGORITHM_ANALYSIS.md +309 -0
  15. agilerl-2.4.2.dev0/DQN_LEARNING_ANALYSIS.md +168 -0
  16. agilerl-2.4.2.dev0/GPU_CLEANUP_ANALYSIS.md +541 -0
  17. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/PKG-INFO +42 -44
  18. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/bc_lm.py +2 -2
  19. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/core/base.py +3 -0
  20. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/dqn.py +5 -25
  21. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/ilql.py +5 -5
  22. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/q_networks.py +2 -2
  23. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/protocols.py +2 -2
  24. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_off_policy.py +1 -1
  25. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/algo_utils.py +2 -2
  26. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/llm_utils.py +0 -3
  27. agilerl-2.4.2.dev0/benchmarking/benchmarking_bandits.py +137 -0
  28. agilerl-2.4.2.dev0/benchmarking/benchmarking_dpo.py +119 -0
  29. agilerl-2.4.2.dev0/benchmarking/benchmarking_grpo.py +218 -0
  30. agilerl-2.4.2.dev0/benchmarking/benchmarking_multi_agent_off_policy.py +216 -0
  31. agilerl-2.4.2.dev0/benchmarking/benchmarking_multi_agent_on_policy.py +167 -0
  32. agilerl-2.4.2.dev0/benchmarking/benchmarking_off_policy.py +168 -0
  33. agilerl-2.4.2.dev0/benchmarking/benchmarking_off_policy_distributed.py +104 -0
  34. agilerl-2.4.2.dev0/benchmarking/benchmarking_offline.py +147 -0
  35. agilerl-2.4.2.dev0/benchmarking/benchmarking_offline_distributed.py +145 -0
  36. agilerl-2.4.2.dev0/benchmarking/benchmarking_on_policy.py +115 -0
  37. agilerl-2.4.2.dev0/benchmarking/benchmarking_rainbow.py +170 -0
  38. agilerl-2.4.2.dev0/benchmarking/benchmarking_recurrent.py +173 -0
  39. agilerl-2.4.2.dev0/benchmarking/benchmarking_resnet.py +107 -0
  40. agilerl-2.4.2.dev0/benchmarking/benchmarking_simba.py +126 -0
  41. agilerl-2.4.2.dev0/benchmarking/configs/ds_config.json +16 -0
  42. agilerl-2.4.2.dev0/benchmarking/make_evolvable_benchmarking.py +491 -0
  43. agilerl-2.4.2.dev0/benchmarking/networks.py +538 -0
  44. agilerl-2.4.2.dev0/configs/accelerate/accelerate.yaml +13 -0
  45. agilerl-2.4.2.dev0/configs/accelerate/grpo_accelerate_config.yaml +25 -0
  46. agilerl-2.4.2.dev0/configs/training/bandit/neural_ts.yaml +53 -0
  47. agilerl-2.4.2.dev0/configs/training/bandit/neural_ucb.yaml +53 -0
  48. agilerl-2.4.2.dev0/configs/training/cqn.yaml +55 -0
  49. agilerl-2.4.2.dev0/configs/training/ddpg/ddpg.yaml +68 -0
  50. agilerl-2.4.2.dev0/configs/training/ddpg/ddpg_lstm.yaml +69 -0
  51. agilerl-2.4.2.dev0/configs/training/ddpg/ddpg_simba.yaml +71 -0
  52. agilerl-2.4.2.dev0/configs/training/dpo.yaml +27 -0
  53. agilerl-2.4.2.dev0/configs/training/dqn/dqn.yaml +56 -0
  54. agilerl-2.4.2.dev0/configs/training/dqn/dqn_lstm.yaml +64 -0
  55. agilerl-2.4.2.dev0/configs/training/dqn/dqn_rainbow.yaml +69 -0
  56. agilerl-2.4.2.dev0/configs/training/grpo.yaml +30 -0
  57. agilerl-2.4.2.dev0/configs/training/multi_agent/ippo.yaml +77 -0
  58. agilerl-2.4.2.dev0/configs/training/multi_agent/ippo_pong.yaml +68 -0
  59. agilerl-2.4.2.dev0/configs/training/multi_agent/maddpg.yaml +93 -0
  60. agilerl-2.4.2.dev0/configs/training/multi_agent/matd3.yaml +70 -0
  61. agilerl-2.4.2.dev0/configs/training/multi_input.yaml +64 -0
  62. agilerl-2.4.2.dev0/configs/training/ppo/ppo.yaml +73 -0
  63. agilerl-2.4.2.dev0/configs/training/ppo/ppo_image.yaml +85 -0
  64. agilerl-2.4.2.dev0/configs/training/ppo/ppo_recurrent.yaml +64 -0
  65. agilerl-2.4.2.dev0/configs/training/td3.yaml +64 -0
  66. agilerl-2.4.2.dev0/data/cartpole/cartpole_random_v1.1.0.h5 +0 -0
  67. agilerl-2.4.2.dev0/data/cartpole/cartpole_v1.1.0.h5 +0 -0
  68. agilerl-2.4.2.dev0/data/pendulum/pendulum_random_v1.1.0.h5 +0 -0
  69. agilerl-2.4.2.dev0/data/pendulum/pendulum_v1.1.0.h5 +0 -0
  70. agilerl-2.4.2.dev0/demos/demo_bandit.py +189 -0
  71. agilerl-2.4.2.dev0/demos/demo_custom_network.py +221 -0
  72. agilerl-2.4.2.dev0/demos/demo_multi_agent.py +257 -0
  73. agilerl-2.4.2.dev0/demos/demo_off_policy.py +197 -0
  74. agilerl-2.4.2.dev0/demos/demo_off_policy_distributed.py +227 -0
  75. agilerl-2.4.2.dev0/demos/demo_offline.py +151 -0
  76. agilerl-2.4.2.dev0/demos/demo_offline_distributed.py +192 -0
  77. agilerl-2.4.2.dev0/demos/demo_on_policy.py +150 -0
  78. agilerl-2.4.2.dev0/demos/demo_on_policy_rnn_cartpole.py +271 -0
  79. agilerl-2.4.2.dev0/demos/demo_on_policy_rnn_memory.py +342 -0
  80. agilerl-2.4.2.dev0/demos/demo_on_policy_rnn_minigrid.py +311 -0
  81. agilerl-2.4.2.dev0/demos/performance_flamegraph_cartpole.py +220 -0
  82. agilerl-2.4.2.dev0/demos/performance_flamegraph_lunar_lander.py +222 -0
  83. agilerl-2.4.2.dev0/demos/performance_flamegraph_lunar_lander_rnn.py +232 -0
  84. agilerl-2.4.2.dev0/demos/performance_flamegraph_rnn_memory.py +270 -0
  85. agilerl-2.4.2.dev0/dependabot.yml +8 -0
  86. agilerl-2.4.2.dev0/docs/Makefile +20 -0
  87. agilerl-2.4.2.dev0/docs/_static/arena-github-badge.svg +1 -0
  88. agilerl-2.4.2.dev0/docs/_static/css/custom.css +0 -0
  89. agilerl-2.4.2.dev0/docs/_static/favicon.ico +0 -0
  90. agilerl-2.4.2.dev0/docs/_static/js/expand_sidebar.js +6 -0
  91. agilerl-2.4.2.dev0/docs/_static/logo_teal.png +0 -0
  92. agilerl-2.4.2.dev0/docs/_static/logo_white.png +0 -0
  93. agilerl-2.4.2.dev0/docs/_static/module.png +0 -0
  94. agilerl-2.4.2.dev0/docs/_static/network.png +0 -0
  95. agilerl-2.4.2.dev0/docs/_static/thumbnails/iris-thumbnail.png +0 -0
  96. agilerl-2.4.2.dev0/docs/_static/thumbnails/pendigits-thumbnail.png +0 -0
  97. agilerl-2.4.2.dev0/docs/_static/thumbnails/rainbow_performance.png +0 -0
  98. agilerl-2.4.2.dev0/docs/_static/thumbnails/simba_thumbnail.png +0 -0
  99. agilerl-2.4.2.dev0/docs/api/algorithms/base.rst +292 -0
  100. agilerl-2.4.2.dev0/docs/api/algorithms/cql.rst +174 -0
  101. agilerl-2.4.2.dev0/docs/api/algorithms/ddpg.rst +169 -0
  102. agilerl-2.4.2.dev0/docs/api/algorithms/dpo.rst +122 -0
  103. agilerl-2.4.2.dev0/docs/api/algorithms/dqn.rst +166 -0
  104. agilerl-2.4.2.dev0/docs/api/algorithms/dqn_rainbow.rst +175 -0
  105. agilerl-2.4.2.dev0/docs/api/algorithms/grpo.rst +84 -0
  106. agilerl-2.4.2.dev0/docs/api/algorithms/ilql.rst +16 -0
  107. agilerl-2.4.2.dev0/docs/api/algorithms/index.rst +155 -0
  108. agilerl-2.4.2.dev0/docs/api/algorithms/ippo.rst +344 -0
  109. agilerl-2.4.2.dev0/docs/api/algorithms/maddpg.rst +266 -0
  110. agilerl-2.4.2.dev0/docs/api/algorithms/matd3.rst +265 -0
  111. agilerl-2.4.2.dev0/docs/api/algorithms/neural_ts.rst +154 -0
  112. agilerl-2.4.2.dev0/docs/api/algorithms/neural_ucb.rst +155 -0
  113. agilerl-2.4.2.dev0/docs/api/algorithms/ppo.rst +222 -0
  114. agilerl-2.4.2.dev0/docs/api/algorithms/registry.rst +19 -0
  115. agilerl-2.4.2.dev0/docs/api/algorithms/td3.rst +160 -0
  116. agilerl-2.4.2.dev0/docs/api/algorithms/wrappers.rst +10 -0
  117. agilerl-2.4.2.dev0/docs/api/components/data.rst +46 -0
  118. agilerl-2.4.2.dev0/docs/api/components/index.rst +12 -0
  119. agilerl-2.4.2.dev0/docs/api/components/multi_agent_replay_buffer.rst +27 -0
  120. agilerl-2.4.2.dev0/docs/api/components/replay_buffer.rst +35 -0
  121. agilerl-2.4.2.dev0/docs/api/components/rollout_buffer.rst +61 -0
  122. agilerl-2.4.2.dev0/docs/api/components/sampler.rst +37 -0
  123. agilerl-2.4.2.dev0/docs/api/components/segment_tree.rst +37 -0
  124. agilerl-2.4.2.dev0/docs/api/hpo/index.rst +14 -0
  125. agilerl-2.4.2.dev0/docs/api/hpo/mutation.rst +45 -0
  126. agilerl-2.4.2.dev0/docs/api/hpo/tournament.rst +28 -0
  127. agilerl-2.4.2.dev0/docs/api/modules/base.rst +33 -0
  128. agilerl-2.4.2.dev0/docs/api/modules/bert.rst +17 -0
  129. agilerl-2.4.2.dev0/docs/api/modules/cnn.rst +10 -0
  130. agilerl-2.4.2.dev0/docs/api/modules/custom_activation.rst +7 -0
  131. agilerl-2.4.2.dev0/docs/api/modules/dummy.rst +14 -0
  132. agilerl-2.4.2.dev0/docs/api/modules/gpt.rst +26 -0
  133. agilerl-2.4.2.dev0/docs/api/modules/index.rst +26 -0
  134. agilerl-2.4.2.dev0/docs/api/modules/lstm.rst +10 -0
  135. agilerl-2.4.2.dev0/docs/api/modules/mlp.rst +10 -0
  136. agilerl-2.4.2.dev0/docs/api/modules/multi_input.rst +10 -0
  137. agilerl-2.4.2.dev0/docs/api/modules/resnet.rst +12 -0
  138. agilerl-2.4.2.dev0/docs/api/modules/simba.rst +12 -0
  139. agilerl-2.4.2.dev0/docs/api/networks/actors.rst +28 -0
  140. agilerl-2.4.2.dev0/docs/api/networks/base.rst +10 -0
  141. agilerl-2.4.2.dev0/docs/api/networks/index.rst +18 -0
  142. agilerl-2.4.2.dev0/docs/api/networks/q_networks.rst +28 -0
  143. agilerl-2.4.2.dev0/docs/api/networks/value_networks.rst +10 -0
  144. agilerl-2.4.2.dev0/docs/api/rollouts/index.rst +10 -0
  145. agilerl-2.4.2.dev0/docs/api/rollouts/on_policy.rst +42 -0
  146. agilerl-2.4.2.dev0/docs/api/train.rst +23 -0
  147. agilerl-2.4.2.dev0/docs/api/utils/algo_utils.rst +105 -0
  148. agilerl-2.4.2.dev0/docs/api/utils/cache.rst +7 -0
  149. agilerl-2.4.2.dev0/docs/api/utils/evolvable_networks.rst +65 -0
  150. agilerl-2.4.2.dev0/docs/api/utils/ilql_utils.rst +12 -0
  151. agilerl-2.4.2.dev0/docs/api/utils/index.rst +16 -0
  152. agilerl-2.4.2.dev0/docs/api/utils/llm_utils.rst +4 -0
  153. agilerl-2.4.2.dev0/docs/api/utils/log_utils.rst +9 -0
  154. agilerl-2.4.2.dev0/docs/api/utils/minari_utils.rst +8 -0
  155. agilerl-2.4.2.dev0/docs/api/utils/probe_envs.rst +386 -0
  156. agilerl-2.4.2.dev0/docs/api/utils/torch_utils.rst +12 -0
  157. agilerl-2.4.2.dev0/docs/api/utils/utils.rst +30 -0
  158. agilerl-2.4.2.dev0/docs/api/vector/index.rst +8 -0
  159. agilerl-2.4.2.dev0/docs/api/vector/petting_zoo_async_vector_env.rst +62 -0
  160. agilerl-2.4.2.dev0/docs/api/vector/petting_zoo_vector_env.rst +10 -0
  161. agilerl-2.4.2.dev0/docs/api/wrappers/agent.rst +28 -0
  162. agilerl-2.4.2.dev0/docs/api/wrappers/index.rst +10 -0
  163. agilerl-2.4.2.dev0/docs/api/wrappers/learning.rst +17 -0
  164. agilerl-2.4.2.dev0/docs/api/wrappers/make_evolvable.rst +8 -0
  165. agilerl-2.4.2.dev0/docs/api/wrappers/pettingzoo.rst +8 -0
  166. agilerl-2.4.2.dev0/docs/bandits/index.rst +336 -0
  167. agilerl-2.4.2.dev0/docs/conf.py +79 -0
  168. agilerl-2.4.2.dev0/docs/custom_algorithms/index.rst +75 -0
  169. agilerl-2.4.2.dev0/docs/debugging_rl/index.rst +308 -0
  170. agilerl-2.4.2.dev0/docs/distributed_training/index.rst +250 -0
  171. agilerl-2.4.2.dev0/docs/evo_hyperparam_opt/index.rst +242 -0
  172. agilerl-2.4.2.dev0/docs/evolvable_networks/index.rst +589 -0
  173. agilerl-2.4.2.dev0/docs/get_started/agilerl2changes.rst +66 -0
  174. agilerl-2.4.2.dev0/docs/get_started/index.rst +440 -0
  175. agilerl-2.4.2.dev0/docs/index.rst +148 -0
  176. agilerl-2.4.2.dev0/docs/llm_finetuning/index.rst +57 -0
  177. agilerl-2.4.2.dev0/docs/make.bat +35 -0
  178. agilerl-2.4.2.dev0/docs/multi_agent_training/index.rst +698 -0
  179. agilerl-2.4.2.dev0/docs/off_policy/index.rst +340 -0
  180. agilerl-2.4.2.dev0/docs/offline_training/index.rst +300 -0
  181. agilerl-2.4.2.dev0/docs/on_policy/index.rst +503 -0
  182. agilerl-2.4.2.dev0/docs/pomdp/index.rst +35 -0
  183. agilerl-2.4.2.dev0/docs/releases/index.rst +7 -0
  184. agilerl-2.4.2.dev0/docs/requirements.txt +5 -0
  185. agilerl-2.4.2.dev0/find_dqn_commit.sh +82 -0
  186. agilerl-2.4.2.dev0/pyproject.toml +92 -0
  187. agilerl-2.4.2.dev0/pytest.ini +31 -0
  188. agilerl-2.4.2.dev0/tests/__init__.py +0 -0
  189. agilerl-2.4.2.dev0/tests/conftest.py +312 -0
  190. agilerl-2.4.2.dev0/tests/helper_functions.py +345 -0
  191. agilerl-2.4.2.dev0/tests/pz_vector_test_utils.py +230 -0
  192. agilerl-2.4.2.dev0/tests/test_algorithms/__init__.py +0 -0
  193. agilerl-2.4.2.dev0/tests/test_algorithms/test_bandits/__init__.py +0 -0
  194. agilerl-2.4.2.dev0/tests/test_algorithms/test_bandits/test_neural_ts.py +411 -0
  195. agilerl-2.4.2.dev0/tests/test_algorithms/test_bandits/test_neural_ucb.py +423 -0
  196. agilerl-2.4.2.dev0/tests/test_algorithms/test_base.py +1293 -0
  197. agilerl-2.4.2.dev0/tests/test_algorithms/test_bc_lm.py +1157 -0
  198. agilerl-2.4.2.dev0/tests/test_algorithms/test_llms/__init__.py +0 -0
  199. agilerl-2.4.2.dev0/tests/test_algorithms/test_llms/conftest.py +97 -0
  200. agilerl-2.4.2.dev0/tests/test_algorithms/test_llms/test_dpo.py +485 -0
  201. agilerl-2.4.2.dev0/tests/test_algorithms/test_llms/test_grpo.py +3794 -0
  202. agilerl-2.4.2.dev0/tests/test_algorithms/test_multi_agent/__init__.py +0 -0
  203. agilerl-2.4.2.dev0/tests/test_algorithms/test_multi_agent/test_ippo.py +1749 -0
  204. agilerl-2.4.2.dev0/tests/test_algorithms/test_multi_agent/test_maddpg.py +1365 -0
  205. agilerl-2.4.2.dev0/tests/test_algorithms/test_multi_agent/test_matd3.py +1488 -0
  206. agilerl-2.4.2.dev0/tests/test_algorithms/test_optimizer_wrapper.py +844 -0
  207. agilerl-2.4.2.dev0/tests/test_algorithms/test_registry.py +826 -0
  208. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/__init__.py +0 -0
  209. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_cqn.py +516 -0
  210. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_ddpg.py +701 -0
  211. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_dqn.py +550 -0
  212. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_dqn_rainbow.py +714 -0
  213. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_ilql.py +682 -0
  214. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_ppo.py +1347 -0
  215. agilerl-2.4.2.dev0/tests/test_algorithms/test_single_agent/test_td3.py +879 -0
  216. agilerl-2.4.2.dev0/tests/test_components/__init__.py +0 -0
  217. agilerl-2.4.2.dev0/tests/test_components/test_multi_agent_replay_buffer.py +621 -0
  218. agilerl-2.4.2.dev0/tests/test_components/test_replay_buffer.py +846 -0
  219. agilerl-2.4.2.dev0/tests/test_components/test_replay_data.py +60 -0
  220. agilerl-2.4.2.dev0/tests/test_components/test_rollout_buffer.py +1763 -0
  221. agilerl-2.4.2.dev0/tests/test_components/test_sampler.py +354 -0
  222. agilerl-2.4.2.dev0/tests/test_components/test_segment_tree.py +126 -0
  223. agilerl-2.4.2.dev0/tests/test_data.py +319 -0
  224. agilerl-2.4.2.dev0/tests/test_hpo/__init__.py +0 -0
  225. agilerl-2.4.2.dev0/tests/test_hpo/test_mutation.py +1645 -0
  226. agilerl-2.4.2.dev0/tests/test_hpo/test_tournament.py +379 -0
  227. agilerl-2.4.2.dev0/tests/test_modules/__init__.py +0 -0
  228. agilerl-2.4.2.dev0/tests/test_modules/test_base.py +514 -0
  229. agilerl-2.4.2.dev0/tests/test_modules/test_bert.py +323 -0
  230. agilerl-2.4.2.dev0/tests/test_modules/test_cnn.py +738 -0
  231. agilerl-2.4.2.dev0/tests/test_modules/test_custom_activation.py +23 -0
  232. agilerl-2.4.2.dev0/tests/test_modules/test_dummy.py +32 -0
  233. agilerl-2.4.2.dev0/tests/test_modules/test_gpt.py +307 -0
  234. agilerl-2.4.2.dev0/tests/test_modules/test_lstm.py +283 -0
  235. agilerl-2.4.2.dev0/tests/test_modules/test_make_evolvable.py +1093 -0
  236. agilerl-2.4.2.dev0/tests/test_modules/test_mlp.py +259 -0
  237. agilerl-2.4.2.dev0/tests/test_modules/test_multi_input.py +1016 -0
  238. agilerl-2.4.2.dev0/tests/test_modules/test_resnet.py +255 -0
  239. agilerl-2.4.2.dev0/tests/test_modules/test_simba.py +166 -0
  240. agilerl-2.4.2.dev0/tests/test_networks/__init__.py +0 -0
  241. agilerl-2.4.2.dev0/tests/test_networks/test_actors.py +908 -0
  242. agilerl-2.4.2.dev0/tests/test_networks/test_base.py +221 -0
  243. agilerl-2.4.2.dev0/tests/test_networks/test_q_networks.py +471 -0
  244. agilerl-2.4.2.dev0/tests/test_networks/test_value_functions.py +174 -0
  245. agilerl-2.4.2.dev0/tests/test_protocols.py +189 -0
  246. agilerl-2.4.2.dev0/tests/test_train/test_train.py +4627 -0
  247. agilerl-2.4.2.dev0/tests/test_train/test_train_llm.py +781 -0
  248. agilerl-2.4.2.dev0/tests/test_utils/__init__.py +0 -0
  249. agilerl-2.4.2.dev0/tests/test_utils/test_algo_utils.py +819 -0
  250. agilerl-2.4.2.dev0/tests/test_utils/test_cache.py +57 -0
  251. agilerl-2.4.2.dev0/tests/test_utils/test_ilql_utils.py +80 -0
  252. agilerl-2.4.2.dev0/tests/test_utils/test_llm_utils.py +893 -0
  253. agilerl-2.4.2.dev0/tests/test_utils/test_log_utils.py +115 -0
  254. agilerl-2.4.2.dev0/tests/test_utils/test_minari_utils.py +171 -0
  255. agilerl-2.4.2.dev0/tests/test_utils/test_probe_envs.py +668 -0
  256. agilerl-2.4.2.dev0/tests/test_utils/test_probe_envs_ma.py +732 -0
  257. agilerl-2.4.2.dev0/tests/test_utils/test_sampling_utils.py +175 -0
  258. agilerl-2.4.2.dev0/tests/test_utils/test_torch_utils.py +106 -0
  259. agilerl-2.4.2.dev0/tests/test_utils/test_utils.py +537 -0
  260. agilerl-2.4.2.dev0/tests/test_utils/test_utils_evolvable.py +559 -0
  261. agilerl-2.4.2.dev0/tests/test_vector/test_vector.py +1568 -0
  262. agilerl-2.4.2.dev0/tests/test_wrappers/__init__.py +0 -0
  263. agilerl-2.4.2.dev0/tests/test_wrappers/test_agent.py +817 -0
  264. agilerl-2.4.2.dev0/tests/test_wrappers/test_autoreset.py +203 -0
  265. agilerl-2.4.2.dev0/tests/test_wrappers/test_bandit_env.py +40 -0
  266. agilerl-2.4.2.dev0/tests/test_wrappers/test_skills.py +61 -0
  267. agilerl-2.4.2.dev0/uv.lock +5547 -0
  268. agilerl-2.4.1.dev3/pyproject.toml +0 -68
  269. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/LICENSE +0 -0
  270. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/README.md +0 -0
  271. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/__init__.py +0 -0
  272. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/__init__.py +0 -0
  273. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/core/__init__.py +0 -0
  274. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/core/optimizer_wrapper.py +0 -0
  275. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/core/registry.py +0 -0
  276. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/cqn.py +0 -0
  277. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/ddpg.py +0 -0
  278. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/dpo.py +0 -0
  279. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/dqn_rainbow.py +0 -0
  280. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/grpo.py +0 -0
  281. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/ippo.py +0 -0
  282. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/maddpg.py +0 -0
  283. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/matd3.py +0 -0
  284. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/neural_ts_bandit.py +0 -0
  285. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/neural_ucb_bandit.py +0 -0
  286. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/ppo.py +0 -0
  287. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/algorithms/td3.py +0 -0
  288. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/__init__.py +0 -0
  289. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/data.py +0 -0
  290. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/multi_agent_replay_buffer.py +0 -0
  291. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/replay_buffer.py +0 -0
  292. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/rollout_buffer.py +0 -0
  293. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/sampler.py +0 -0
  294. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/components/segment_tree.py +0 -0
  295. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/data/__init__.py +0 -0
  296. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/data/language_environment.py +0 -0
  297. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/data/rl_data.py +0 -0
  298. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/data/tokenizer.py +0 -0
  299. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/data/torch_datasets.py +0 -0
  300. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/hpo/__init__.py +0 -0
  301. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/hpo/mutation.py +0 -0
  302. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/hpo/tournament.py +0 -0
  303. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/__init__.py +0 -0
  304. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/base.py +0 -0
  305. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/bert.py +0 -0
  306. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/cnn.py +0 -0
  307. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/configs.py +0 -0
  308. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/custom_components.py +0 -0
  309. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/dummy.py +0 -0
  310. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/gpt.py +0 -0
  311. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/lstm.py +0 -0
  312. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/mlp.py +0 -0
  313. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/multi_input.py +0 -0
  314. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/resnet.py +0 -0
  315. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/modules/simba.py +0 -0
  316. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/__init__.py +0 -0
  317. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/actors.py +0 -0
  318. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/base.py +0 -0
  319. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/custom_modules.py +0 -0
  320. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/distributions.py +0 -0
  321. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/distributions_experimental.py +0 -0
  322. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/networks/value_networks.py +0 -0
  323. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/rollouts/__init__.py +0 -0
  324. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/rollouts/on_policy.py +0 -0
  325. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/__init__.py +0 -0
  326. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_bandits.py +0 -0
  327. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_llm.py +0 -0
  328. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_multi_agent_off_policy.py +0 -0
  329. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_multi_agent_on_policy.py +0 -0
  330. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_offline.py +0 -0
  331. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/training/train_on_policy.py +0 -0
  332. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/typing.py +0 -0
  333. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/__init__.py +0 -0
  334. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/cache.py +0 -0
  335. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/evolvable_networks.py +0 -0
  336. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/ilql_utils.py +0 -0
  337. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/log_utils.py +0 -0
  338. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/minari_utils.py +0 -0
  339. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/probe_envs.py +0 -0
  340. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/probe_envs_ma.py +0 -0
  341. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/sampling_utils.py +0 -0
  342. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/torch_utils.py +0 -0
  343. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/utils/utils.py +0 -0
  344. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/vector/__init__.py +0 -0
  345. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/vector/pz_async_vec_env.py +0 -0
  346. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/vector/pz_vec_env.py +0 -0
  347. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/__init__.py +0 -0
  348. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/agent.py +0 -0
  349. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/learning.py +0 -0
  350. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/make_evolvable.py +0 -0
  351. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/pettingzoo_wrappers.py +0 -0
  352. {agilerl-2.4.1.dev3 → agilerl-2.4.2.dev0}/agilerl/wrappers/utils.py +0 -0
@@ -0,0 +1,9 @@
1
+ [run]
2
+ concurrency = multiprocessing
3
+ parallel = true
4
+ sigterm = true
5
+
6
+ [report]
7
+ exclude_lines =
8
+ pragma: no cover
9
+ if TYPE_CHECKING:
@@ -0,0 +1,27 @@
1
+ ---
2
+ name: Bug report
3
+ about: Create a report to help us improve
4
+ title: ''
5
+ labels: bug
6
+ assignees: ''
7
+
8
+ ---
9
+
10
+ **What version of AgileRL are you using?**
11
+ **What operating system and processor architecture are you using?**
12
+
13
+ **What did you do?**
14
+ Steps to reproduce the behaviour:
15
+ 1. Go to '...'
16
+ 2. Click on '....'
17
+ 3. Scroll down to '....'
18
+ 4. See error
19
+
20
+ **What did you expect to see?**
21
+ A clear and concise description of what you expected to happen.
22
+
23
+ **What did you see instead? Describe the bug.**
24
+ A clear and concise description of what the bug is.
25
+
26
+ **Additional context**
27
+ Add any other context about the problem here.
@@ -0,0 +1,20 @@
1
+ ---
2
+ name: Feature request
3
+ about: Suggest an idea for this project
4
+ title: ''
5
+ labels: ''
6
+ assignees: ''
7
+
8
+ ---
9
+
10
+ **Is your feature request related to a problem? Please describe.**
11
+ A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
12
+
13
+ **Describe the solution you'd like**
14
+ A clear and concise description of what you want to happen.
15
+
16
+ **Describe alternatives you've considered**
17
+ A clear and concise description of any alternative solutions or features you've considered.
18
+
19
+ **Additional context**
20
+ Add any other context or screenshots about the feature request here.
@@ -0,0 +1,34 @@
1
+ # Pull Request
2
+
3
+ ## Description
4
+
5
+ Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context.
6
+
7
+ Fixes # (issue)
8
+
9
+ ## Type of change
10
+
11
+ Please delete options that are not relevant.
12
+
13
+ - [ ] Bug fix (non-breaking change which fixes an issue)
14
+ - [ ] New feature (non-breaking change which adds functionality)
15
+ - [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
16
+ - [ ] Documentation update
17
+
18
+ ## How Has This Been Tested?
19
+
20
+ Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce.
21
+
22
+ - [ ] Test A
23
+ - [ ] Test B
24
+
25
+ ## Checklist:
26
+
27
+ - [ ] My code follows the style guidelines of this project
28
+ - [ ] I have performed a self-review of my own code
29
+ - [ ] I have commented my code, particularly in hard-to-understand areas
30
+ - [ ] I have made corresponding changes to the documentation
31
+ - [ ] My changes generate no new warnings
32
+ - [ ] I have added tests that prove my fix is effective or that my feature works
33
+ - [ ] New and existing unit tests pass locally with my changes
34
+ - [ ] Any dependent changes have been merged and published in downstream modules
@@ -0,0 +1,24 @@
1
+ <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="65" height="20" role="img"
2
+ aria-label="Arena">
3
+ <title>Arena</title>
4
+ <linearGradient id="s" x2="0" y2="100%">
5
+ <stop offset="0" stop-color="#bbb" stop-opacity=".1" />
6
+ <stop offset="1" stop-opacity=".1" />
7
+ </linearGradient>
8
+ <clipPath id="r">
9
+ <rect width="65" height="20" rx="3" fill="#fff" />
10
+ </clipPath>
11
+ <g clip-path="url(#r)">
12
+ <rect width="24" height="20" fill="#555" />
13
+ <rect x="24" width="41" height="20" fill="#467f81" />
14
+ <rect width="65" height="20" fill="url(#s)" />
15
+ </g>
16
+ <g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif"
17
+ text-rendering="geometricPrecision" font-size="110">
18
+ <image x="5" y="3" width="14" height="14"
19
+ xlink:href="data:image/jpeg;base64,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" />
20
+ <text aria-hidden="true" x="435" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)"
21
+ textLength="310">Arena</text><text x="435" y="140" transform="scale(.1)" fill="#fff"
22
+ textLength="310">Arena</text>
23
+ </g>
24
+ </svg>
@@ -0,0 +1,101 @@
1
+ ---
2
+ # For most projects, this workflow file will not need changing; you simply need
3
+ # to commit it to your repository.
4
+ #
5
+ # You may wish to alter this file to override the set of languages analyzed,
6
+ # or to provide custom queries or build logic.
7
+ #
8
+ # ******** NOTE ********
9
+ # We have attempted to detect the languages in your repository. Please check
10
+ # the `language` matrix defined below to confirm you have the correct set of
11
+ # supported CodeQL languages.
12
+ #
13
+ name: CodeQL Advanced
14
+
15
+ on:
16
+ push:
17
+ branches: [main]
18
+ pull_request:
19
+ branches: [main]
20
+ schedule:
21
+ - cron: 40 9 * * 4
22
+
23
+ jobs:
24
+ analyze:
25
+ name: Analyze (${{ matrix.language }})
26
+ # Runner size impacts CodeQL analysis time. To learn more, please see:
27
+ # - https://gh.io/recommended-hardware-resources-for-running-codeql
28
+ # - https://gh.io/supported-runners-and-hardware-resources
29
+ # - https://gh.io/using-larger-runners (GitHub.com only)
30
+ # Consider using larger runners or machines with greater resources for possible analysis time improvements.
31
+ runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
32
+ permissions:
33
+ # required for all workflows
34
+ security-events: write
35
+
36
+ # required to fetch internal or private CodeQL packs
37
+ packages: read
38
+
39
+ # only required for workflows in private repositories
40
+ actions: read
41
+ contents: read
42
+
43
+ strategy:
44
+ fail-fast: false
45
+ matrix:
46
+ include:
47
+ - language: actions
48
+ build-mode: none
49
+ - language: python
50
+ build-mode: none
51
+ # CodeQL supports the following values keywords for 'language': 'actions', 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'rust', 'swift'
52
+ # Use `c-cpp` to analyze code written in C, C++ or both
53
+ # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
54
+ # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
55
+ # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
56
+ # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
57
+ # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
58
+ # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
59
+ steps:
60
+ - name: Checkout repository
61
+ uses: actions/checkout@v4
62
+
63
+ # Add any setup steps before running the `github/codeql-action/init` action.
64
+ # This includes steps like installing compilers or runtimes (`actions/setup-node`
65
+ # or others). This is typically only required for manual builds.
66
+ # - name: Setup runtime (example)
67
+ # uses: actions/setup-example@v1
68
+
69
+ # Initializes the CodeQL tools for scanning.
70
+ - name: Initialize CodeQL
71
+ uses: github/codeql-action/init@v3
72
+ with:
73
+ languages: ${{ matrix.language }}
74
+ build-mode: ${{ matrix.build-mode }}
75
+ # If you wish to specify custom queries, you can do so here or in a config file.
76
+ # By default, queries listed here will override any specified in a config file.
77
+ # Prefix the list here with "+" to use these queries and those in the config file.
78
+
79
+ # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
80
+ # queries: security-extended,security-and-quality
81
+
82
+ # If the analyze step fails for one of the languages you are analyzing with
83
+ # "We were unable to automatically build your code", modify the matrix above
84
+ # to set the build mode to "manual" for that language. Then modify this step
85
+ # to build your code.
86
+ # ℹ️ Command-line programs to run using the OS shell.
87
+ # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
88
+ - if: matrix.build-mode == 'manual'
89
+ shell: bash
90
+ run: |
91
+ echo 'If you are using a "manual" build mode for one or more of the' \
92
+ 'languages you are analyzing, replace this with the commands to build' \
93
+ 'your code, for example:'
94
+ echo ' make bootstrap'
95
+ echo ' make release'
96
+ exit 1
97
+
98
+ - name: Perform CodeQL Analysis
99
+ uses: github/codeql-action/analyze@v3
100
+ with:
101
+ category: /language:${{matrix.language}}
@@ -0,0 +1,59 @@
1
+ ---
2
+ name: Python application
3
+
4
+ on:
5
+ push:
6
+ branches: [main, nightly]
7
+ paths:
8
+ - agilerl/**
9
+ pull_request:
10
+ branches: [main, nightly]
11
+ paths:
12
+ - agilerl/**
13
+
14
+ permissions:
15
+ contents: read
16
+
17
+ jobs:
18
+ build:
19
+ runs-on: gha-runner-scale-set
20
+ container:
21
+ image: pytorch/pytorch:2.7.1-cuda12.6-cudnn9-devel
22
+ options: --user root
23
+ # todo: test on different python versions!
24
+ # strategy:
25
+ # matrix:
26
+ # python-version: ["3.10", "3.11", "3.12"]
27
+ steps:
28
+ - uses: actions/checkout@v4
29
+ # - name: Set up Python 3.11
30
+ # uses: actions/setup-python@v4
31
+ # with:
32
+ # python-version: '3.11'
33
+ - name: Install dependencies
34
+ run: |
35
+ python -m pip install --upgrade pip
36
+
37
+ # Use uv for faster downloads
38
+ pip install uv
39
+ uv pip install --system ruff pytest pytest-cov black codespell yamlfmt isort pyupgrade
40
+ uv pip install --system -e .[llm]
41
+ - name: Run black
42
+ run: |
43
+ black .
44
+ - name: Spellcheck with codespell
45
+ run: |
46
+ codespell --skip=*.css,*.js,*.map,*.scss,*.svg --ignore-words-list=magent,pres,roate
47
+ - name: Lint with ruff
48
+ run: |
49
+ ruff check .
50
+ - name: Run pyupgrade
51
+ run: |
52
+ pyupgrade --py38-plus
53
+ - name: Test with pytest
54
+ run: |
55
+ pytest --exitfirst --cov=agilerl --cov-report=xml
56
+ - name: Upload coverage reports to Codecov
57
+ uses: codecov/codecov-action@v3
58
+ env:
59
+ CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
@@ -0,0 +1,145 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ pip-wheel-metadata/
24
+ share/python-wheels/
25
+ *.egg-info/
26
+ .installed.cfg
27
+ *.egg
28
+ MANIFEST
29
+ .DS_Store
30
+
31
+ # PyInstaller
32
+ # Usually these files are written by a python script from a template
33
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
34
+ *.manifest
35
+ *.spec
36
+
37
+ # Installer logs
38
+ pip-log.txt
39
+ pip-delete-this-directory.txt
40
+
41
+ # Unit test / coverage reports
42
+ htmlcov/
43
+ .tox/
44
+ .nox/
45
+ .coverage
46
+ .coverage.*
47
+ .cache
48
+ nosetests.xml
49
+ coverage.xml
50
+ *.cover
51
+ *.py,cover
52
+ .hypothesis/
53
+ .pytest_cache/
54
+
55
+ # Translations
56
+ *.mo
57
+ *.pot
58
+
59
+ # Django stuff:
60
+ *.log
61
+ local_settings.py
62
+ db.sqlite3
63
+ db.sqlite3-journal
64
+
65
+ # Flask stuff:
66
+ instance/
67
+ .webassets-cache
68
+
69
+ # Scrapy stuff:
70
+ .scrapy
71
+
72
+ # Sphinx documentation
73
+ docs/_build/
74
+
75
+ # PyBuilder
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+ **.ipynb
81
+
82
+ # IPython
83
+ profile_default/
84
+ ipython_config.py
85
+
86
+ # pyenv
87
+ .python-version
88
+
89
+ # pipenv
90
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
91
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
92
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
93
+ # install all needed dependencies.
94
+ #Pipfile.lock
95
+
96
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow
97
+ __pypackages__/
98
+
99
+ # Celery stuff
100
+ celerybeat-schedule
101
+ celerybeat.pid
102
+
103
+ # SageMath parsed files
104
+ *.sage.py
105
+
106
+ # Environments
107
+ .env
108
+ .vscode/
109
+ .venv
110
+ # env/
111
+ venv/
112
+ # ENV/
113
+ env.bak/
114
+ venv.bak/
115
+
116
+ # Spyder project settings
117
+ .spyderproject
118
+ .spyproject
119
+
120
+ # Rope project settings
121
+ .ropeproject
122
+
123
+ # mkdocs documentation
124
+ /site
125
+
126
+ # mypy
127
+ .mypy_cache/
128
+ .dmypy.json
129
+ dmypy.json
130
+
131
+ # Pyre type checker
132
+ .pyre/
133
+
134
+ # Saved models
135
+ outputs/
136
+
137
+ # Ruff
138
+ .ruff_cache/
139
+
140
+ # Large data files
141
+ data/wordle/
142
+ data/wordle.zip
143
+
144
+ # WandB
145
+ wandb/
@@ -0,0 +1,58 @@
1
+ ---
2
+ # See https://pre-commit.com for more information
3
+ # See https://pre-commit.com/hooks.html for more hooks
4
+ ci:
5
+ autoupdate_branch: nightly
6
+ repos:
7
+ - repo: https://github.com/pre-commit/pre-commit-hooks
8
+ rev: v6.0.0
9
+ hooks:
10
+ - id: check-symlinks
11
+ - id: destroyed-symlinks
12
+ - id: trailing-whitespace
13
+ - id: end-of-file-fixer
14
+ - id: check-yaml
15
+ - id: check-toml
16
+ - id: check-ast
17
+ - id: check-added-large-files
18
+ args: [--maxkb=10000]
19
+ - id: check-merge-conflict
20
+ - id: check-executables-have-shebangs
21
+ - id: check-shebang-scripts-are-executable
22
+ - id: detect-private-key
23
+ - id: debug-statements
24
+ - id: mixed-line-ending
25
+ args: [--fix=lf]
26
+ - repo: https://github.com/psf/black-pre-commit-mirror
27
+ rev: 25.12.0
28
+ hooks:
29
+ - id: black
30
+ - repo: https://github.com/codespell-project/codespell
31
+ rev: v2.4.1
32
+ hooks:
33
+ - id: codespell
34
+ args:
35
+ - --skip=*.css,*.js,*.map,*.scss,*.svg
36
+ - --ignore-words-list=magent,pres,roate
37
+ - repo: https://github.com/astral-sh/ruff-pre-commit
38
+ rev: v0.14.9
39
+ hooks:
40
+ - id: ruff-check
41
+ args:
42
+ - --select=I
43
+ - --fix
44
+ - --ignore=E501,F401
45
+ - repo: https://github.com/asottile/pyupgrade
46
+ rev: v3.21.2
47
+ hooks:
48
+ - id: pyupgrade
49
+ args: [--py38-plus]
50
+ - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt
51
+ rev: 0.2.3
52
+ hooks:
53
+ - id: yamlfmt
54
+ - repo: https://github.com/astral-sh/uv-pre-commit
55
+ # uv version.
56
+ rev: 0.9.27
57
+ hooks:
58
+ - id: uv-lock
@@ -0,0 +1,30 @@
1
+ ---
2
+ # .readthedocs.yaml
3
+ # Read the Docs configuration file
4
+ # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
5
+
6
+ # Required
7
+ version: 2
8
+
9
+ # Set the version of Python and other tools you might need
10
+ build:
11
+ os: ubuntu-22.04
12
+ tools:
13
+ python: '3.10'
14
+
15
+ # Build documentation in the docs/ directory with Sphinx
16
+ sphinx:
17
+ configuration: docs/conf.py
18
+
19
+ # If using Sphinx, optionally build your docs in additional formats such as PDF
20
+ # formats:
21
+ # - pdf
22
+
23
+ # Optionally declare the Python requirements required to build your docs
24
+ python:
25
+ install:
26
+ - requirements: docs/requirements.txt
27
+ - method: pip
28
+ path: .
29
+ extra_requirements:
30
+ - all
@@ -0,0 +1,20 @@
1
+ cff-version: 1.2.0
2
+ title: AgileRL
3
+ message: >-
4
+ If you use this software, please cite it using the
5
+ metadata from this file.
6
+ type: software
7
+ authors:
8
+ - given-names: Nicholas
9
+ family-names: Ustaran-Anderegg
10
+ affiliation: AgileRL
11
+ - given-names: Michael
12
+ family-names: Pratt
13
+ affiliation: AgileRL
14
+ repository-code: 'https://github.com/AgileRL/AgileRL'
15
+ url: 'https://agilerl.com'
16
+ repository: 'https://docs.agilerl.com'
17
+ abstract: >-
18
+ AgileRL is a Deep Reinforcement Learning library focused
19
+ on streamlining development by introducing RLOps.
20
+ license: Apache-2.0