agilerl 2.4.3.dev0__tar.gz → 2.5.0.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 (351) hide show
  1. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.coveragerc +1 -0
  2. agilerl-2.5.0.dev0/.github/workflows/python-app.yml +56 -0
  3. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.gitignore +1 -3
  4. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.pre-commit-config.yaml +8 -16
  5. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/PKG-INFO +7 -8
  6. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/README.md +1 -0
  7. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/bc_lm.py +158 -100
  8. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/base.py +514 -393
  9. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/optimizer_wrapper.py +88 -86
  10. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/registry.py +68 -68
  11. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/cqn.py +30 -25
  12. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ddpg.py +130 -94
  13. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dpo.py +21 -20
  14. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dqn.py +40 -31
  15. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dqn_rainbow.py +81 -45
  16. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/grpo.py +49 -31
  17. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ilql.py +461 -294
  18. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ippo.py +155 -109
  19. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/maddpg.py +122 -98
  20. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/matd3.py +150 -118
  21. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/neural_ts_bandit.py +37 -28
  22. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/neural_ucb_bandit.py +38 -29
  23. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ppo.py +222 -163
  24. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/td3.py +164 -105
  25. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/data.py +19 -17
  26. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/multi_agent_replay_buffer.py +33 -36
  27. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/replay_buffer.py +37 -37
  28. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/rollout_buffer.py +165 -114
  29. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/sampler.py +43 -25
  30. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/segment_tree.py +26 -22
  31. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/language_environment.py +12 -6
  32. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/rl_data.py +75 -23
  33. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/tokenizer.py +13 -13
  34. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/torch_datasets.py +12 -12
  35. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/mutation.py +195 -123
  36. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/tournament.py +16 -18
  37. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/base.py +129 -102
  38. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/bert.py +131 -112
  39. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/cnn.py +95 -77
  40. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/configs.py +45 -41
  41. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/custom_components.py +29 -22
  42. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/dummy.py +7 -5
  43. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/gpt.py +172 -143
  44. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/lstm.py +52 -41
  45. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/mlp.py +43 -34
  46. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/multi_input.py +65 -66
  47. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/resnet.py +24 -19
  48. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/simba.py +25 -18
  49. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/actors.py +116 -90
  50. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/base.py +102 -80
  51. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/custom_modules.py +7 -3
  52. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/distributions.py +49 -33
  53. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/distributions_experimental.py +62 -62
  54. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/q_networks.py +75 -76
  55. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/value_networks.py +16 -16
  56. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/protocols.py +126 -87
  57. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/rollouts/on_policy.py +42 -33
  58. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_bandits.py +47 -39
  59. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_llm.py +116 -107
  60. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_multi_agent_off_policy.py +69 -50
  61. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_multi_agent_on_policy.py +70 -53
  62. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_off_policy.py +103 -67
  63. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_offline.py +49 -46
  64. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_on_policy.py +49 -41
  65. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/typing.py +53 -50
  66. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/algo_utils.py +341 -271
  67. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/cache.py +18 -18
  68. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/evolvable_networks.py +130 -80
  69. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/ilql_utils.py +12 -12
  70. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/llm_utils.py +74 -61
  71. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/log_utils.py +16 -16
  72. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/minari_utils.py +21 -21
  73. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/probe_envs.py +382 -150
  74. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/probe_envs_ma.py +365 -162
  75. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/sampling_utils.py +55 -17
  76. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/torch_utils.py +28 -20
  77. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/utils.py +113 -86
  78. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/pz_async_vec_env.py +138 -107
  79. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/pz_vec_env.py +30 -36
  80. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/agent.py +70 -52
  81. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/learning.py +22 -7
  82. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/make_evolvable.py +317 -247
  83. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/pettingzoo_wrappers.py +16 -9
  84. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/utils.py +13 -6
  85. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_bandits.py +12 -3
  86. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_dpo.py +2 -1
  87. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_grpo.py +9 -7
  88. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_multi_agent_off_policy.py +14 -6
  89. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_multi_agent_on_policy.py +5 -3
  90. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_off_policy.py +22 -14
  91. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_off_policy_distributed.py +3 -3
  92. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_offline.py +4 -2
  93. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_offline_distributed.py +1 -1
  94. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_rainbow.py +3 -1
  95. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_recurrent.py +3 -3
  96. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_simba.py +7 -5
  97. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/make_evolvable_benchmarking.py +28 -13
  98. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/networks.py +73 -42
  99. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg.yaml +4 -2
  100. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_bandit.py +16 -10
  101. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_custom_network.py +10 -9
  102. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_multi_agent.py +10 -7
  103. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_off_policy.py +9 -8
  104. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_off_policy_distributed.py +9 -9
  105. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_offline.py +4 -4
  106. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_offline_distributed.py +9 -8
  107. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy.py +8 -6
  108. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_cartpole.py +20 -11
  109. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_memory.py +25 -15
  110. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_minigrid.py +28 -20
  111. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_cartpole.py +14 -8
  112. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_lunar_lander.py +14 -8
  113. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_lunar_lander_rnn.py +14 -8
  114. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_rnn_memory.py +18 -11
  115. agilerl-2.5.0.dev0/docs/__init__.py +1 -0
  116. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/base.rst +14 -14
  117. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ddpg.rst +29 -2
  118. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/maddpg.rst +8 -0
  119. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/matd3.rst +8 -0
  120. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/td3.rst +29 -4
  121. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/conf.py +3 -3
  122. agilerl-2.5.0.dev0/pyproject.toml +139 -0
  123. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/conftest.py +27 -19
  124. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/helper_functions.py +78 -74
  125. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/pz_vector_test_utils.py +28 -13
  126. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/test_neural_ts.py +32 -13
  127. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/test_neural_ucb.py +32 -13
  128. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_base.py +385 -44
  129. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bc_lm.py +91 -23
  130. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/conftest.py +1 -3
  131. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/test_dpo.py +13 -9
  132. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/test_grpo.py +184 -95
  133. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_ippo.py +123 -53
  134. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_maddpg.py +196 -68
  135. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_matd3.py +211 -74
  136. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_optimizer_wrapper.py +200 -85
  137. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_registry.py +32 -21
  138. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_cqn.py +42 -20
  139. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ddpg.py +124 -72
  140. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_dqn.py +41 -14
  141. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_dqn_rainbow.py +79 -27
  142. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ilql.py +42 -18
  143. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ppo.py +149 -62
  144. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_td3.py +233 -96
  145. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_multi_agent_replay_buffer.py +13 -5
  146. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_replay_buffer.py +1 -1
  147. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_rollout_buffer.py +60 -26
  148. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_data.py +11 -13
  149. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/test_mutation.py +196 -70
  150. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/test_tournament.py +12 -9
  151. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_base.py +58 -0
  152. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_bert.py +29 -7
  153. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_cnn.py +64 -16
  154. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_dummy.py +4 -2
  155. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_gpt.py +14 -4
  156. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_lstm.py +23 -8
  157. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_make_evolvable.py +179 -64
  158. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_mlp.py +24 -10
  159. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_multi_input.py +32 -33
  160. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_simba.py +40 -8
  161. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_actors.py +130 -101
  162. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_base.py +59 -4
  163. agilerl-2.5.0.dev0/tests/test_networks/test_distributions.py +209 -0
  164. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_q_networks.py +118 -25
  165. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_value_functions.py +12 -5
  166. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_protocols.py +67 -18
  167. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_train/test_train.py +392 -217
  168. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_train/test_train_llm.py +16 -21
  169. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_algo_utils.py +123 -23
  170. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_cache.py +2 -2
  171. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_ilql_utils.py +3 -1
  172. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_llm_utils.py +71 -29
  173. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_minari_utils.py +6 -5
  174. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_probe_envs.py +108 -46
  175. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_probe_envs_ma.py +77 -16
  176. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_sampling_utils.py +14 -14
  177. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_torch_utils.py +1 -1
  178. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_utils.py +40 -20
  179. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_utils_evolvable.py +50 -25
  180. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_vector/test_vector.py +161 -106
  181. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_agent.py +84 -45
  182. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_autoreset.py +22 -25
  183. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/uv.lock +1192 -184
  184. agilerl-2.4.3.dev0/.github/workflows/python-app.yml +0 -59
  185. agilerl-2.4.3.dev0/pyproject.toml +0 -92
  186. agilerl-2.4.3.dev0/pytest.ini +0 -31
  187. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
  188. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
  189. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md +0 -0
  190. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/badges/arena-github-badge.svg +0 -0
  191. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/workflows/codeql.yml +0 -0
  192. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.readthedocs.yaml +0 -0
  193. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CITATION.cff +0 -0
  194. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CODE_OF_CONDUCT.md +0 -0
  195. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CONTRIBUTING.md +0 -0
  196. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/LICENSE +0 -0
  197. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/__init__.py +0 -0
  198. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/__init__.py +7 -7
  199. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/__init__.py +2 -2
  200. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/__init__.py +1 -1
  201. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/__init__.py +0 -0
  202. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/__init__.py +0 -0
  203. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/__init__.py +10 -10
  204. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/__init__.py +3 -3
  205. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/rollouts/__init__.py +0 -0
  206. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/__init__.py +0 -0
  207. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/__init__.py +0 -0
  208. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/__init__.py +0 -0
  209. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/__init__.py +0 -0
  210. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_on_policy.py +0 -0
  211. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_resnet.py +0 -0
  212. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/configs/ds_config.json +0 -0
  213. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/accelerate/accelerate.yaml +0 -0
  214. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/accelerate/grpo_accelerate_config.yaml +0 -0
  215. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/bandit/neural_ts.yaml +0 -0
  216. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/bandit/neural_ucb.yaml +0 -0
  217. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/cqn.yaml +0 -0
  218. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg_lstm.yaml +0 -0
  219. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg_simba.yaml +0 -0
  220. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dpo.yaml +0 -0
  221. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn.yaml +0 -0
  222. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn_lstm.yaml +0 -0
  223. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn_rainbow.yaml +0 -0
  224. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/grpo.yaml +0 -0
  225. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/ippo.yaml +0 -0
  226. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/ippo_pong.yaml +0 -0
  227. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/maddpg.yaml +0 -0
  228. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/matd3.yaml +0 -0
  229. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_input.yaml +0 -0
  230. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo.yaml +0 -0
  231. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo_image.yaml +0 -0
  232. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo_recurrent.yaml +0 -0
  233. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/td3.yaml +0 -0
  234. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/cartpole/cartpole_random_v1.1.0.h5 +0 -0
  235. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/cartpole/cartpole_v1.1.0.h5 +0 -0
  236. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/pendulum/pendulum_random_v1.1.0.h5 +0 -0
  237. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/pendulum/pendulum_v1.1.0.h5 +0 -0
  238. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/dependabot.yml +0 -0
  239. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/Makefile +0 -0
  240. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/arena-github-badge.svg +0 -0
  241. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/css/custom.css +0 -0
  242. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/favicon.ico +0 -0
  243. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/js/expand_sidebar.js +0 -0
  244. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/logo_teal.png +0 -0
  245. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/logo_white.png +0 -0
  246. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/module.png +0 -0
  247. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/network.png +0 -0
  248. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/iris-thumbnail.png +0 -0
  249. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/pendigits-thumbnail.png +0 -0
  250. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/rainbow_performance.png +0 -0
  251. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/simba_thumbnail.png +0 -0
  252. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/cql.rst +0 -0
  253. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dpo.rst +0 -0
  254. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dqn.rst +0 -0
  255. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dqn_rainbow.rst +0 -0
  256. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/grpo.rst +0 -0
  257. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ilql.rst +0 -0
  258. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/index.rst +0 -0
  259. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ippo.rst +0 -0
  260. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/neural_ts.rst +0 -0
  261. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/neural_ucb.rst +0 -0
  262. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ppo.rst +0 -0
  263. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/registry.rst +0 -0
  264. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/wrappers.rst +0 -0
  265. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/data.rst +0 -0
  266. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/index.rst +0 -0
  267. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/multi_agent_replay_buffer.rst +0 -0
  268. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/replay_buffer.rst +0 -0
  269. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/rollout_buffer.rst +0 -0
  270. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/sampler.rst +0 -0
  271. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/segment_tree.rst +0 -0
  272. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/index.rst +0 -0
  273. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/mutation.rst +0 -0
  274. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/tournament.rst +0 -0
  275. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/base.rst +0 -0
  276. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/bert.rst +0 -0
  277. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/cnn.rst +0 -0
  278. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/custom_activation.rst +0 -0
  279. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/dummy.rst +0 -0
  280. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/gpt.rst +0 -0
  281. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/index.rst +0 -0
  282. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/lstm.rst +0 -0
  283. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/mlp.rst +0 -0
  284. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/multi_input.rst +0 -0
  285. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/resnet.rst +0 -0
  286. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/simba.rst +0 -0
  287. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/actors.rst +0 -0
  288. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/base.rst +0 -0
  289. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/index.rst +0 -0
  290. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/q_networks.rst +0 -0
  291. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/value_networks.rst +0 -0
  292. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/rollouts/index.rst +0 -0
  293. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/rollouts/on_policy.rst +0 -0
  294. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/train.rst +0 -0
  295. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/algo_utils.rst +0 -0
  296. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/cache.rst +0 -0
  297. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/evolvable_networks.rst +0 -0
  298. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/ilql_utils.rst +0 -0
  299. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/index.rst +0 -0
  300. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/llm_utils.rst +0 -0
  301. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/log_utils.rst +0 -0
  302. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/minari_utils.rst +0 -0
  303. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/probe_envs.rst +0 -0
  304. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/torch_utils.rst +0 -0
  305. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/utils.rst +0 -0
  306. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/index.rst +0 -0
  307. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/petting_zoo_async_vector_env.rst +0 -0
  308. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/petting_zoo_vector_env.rst +0 -0
  309. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/agent.rst +0 -0
  310. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/index.rst +0 -0
  311. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/learning.rst +0 -0
  312. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/make_evolvable.rst +0 -0
  313. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/pettingzoo.rst +0 -0
  314. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/bandits/index.rst +0 -0
  315. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/custom_algorithms/index.rst +0 -0
  316. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/debugging_rl/index.rst +0 -0
  317. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/distributed_training/index.rst +0 -0
  318. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/evo_hyperparam_opt/index.rst +0 -0
  319. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/evolvable_networks/index.rst +0 -0
  320. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/get_started/agilerl2changes.rst +0 -0
  321. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/get_started/index.rst +0 -0
  322. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/index.rst +0 -0
  323. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/llm_finetuning/index.rst +0 -0
  324. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/make.bat +0 -0
  325. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/multi_agent_training/index.rst +0 -0
  326. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/off_policy/index.rst +0 -0
  327. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/offline_training/index.rst +0 -0
  328. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/on_policy/index.rst +0 -0
  329. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/pomdp/index.rst +0 -0
  330. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/releases/index.rst +0 -0
  331. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/requirements.txt +0 -0
  332. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/__init__.py +0 -0
  333. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/__init__.py +0 -0
  334. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/__init__.py +0 -0
  335. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/__init__.py +0 -0
  336. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/__init__.py +0 -0
  337. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/__init__.py +0 -0
  338. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/__init__.py +0 -0
  339. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_replay_data.py +0 -0
  340. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_sampler.py +0 -0
  341. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_segment_tree.py +0 -0
  342. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/__init__.py +0 -0
  343. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/__init__.py +0 -0
  344. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_custom_activation.py +0 -0
  345. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_resnet.py +0 -0
  346. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/__init__.py +0 -0
  347. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/__init__.py +0 -0
  348. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_log_utils.py +0 -0
  349. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/__init__.py +0 -0
  350. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_bandit_env.py +0 -0
  351. {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_skills.py +0 -0
@@ -2,6 +2,7 @@
2
2
  concurrency = multiprocessing
3
3
  parallel = true
4
4
  sigterm = true
5
+ omit = agilerl/networks/distributions_experimental.py
5
6
 
6
7
  [report]
7
8
  exclude_lines =
@@ -0,0 +1,56 @@
1
+ ---
2
+ name: Tests
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
+ strategy:
21
+ fail-fast: false
22
+ max-parallel: 4
23
+ matrix:
24
+ python-version: ['3.10', '3.11', '3.12', '3.13']
25
+
26
+ container:
27
+ image: pytorch/pytorch:2.7.1-cuda12.6-cudnn9-devel
28
+ options: --user root
29
+
30
+ # Workspace (/__w) is ~1GB with little free space; root (/) has plenty. Put cache and venv on /.
31
+ env:
32
+ UV_CACHE_DIR: /tmp/uv-cache
33
+ UV_PROJECT_ENVIRONMENT: /tmp/agilerl-venv
34
+
35
+ steps:
36
+ - uses: actions/checkout@v4
37
+ - uses: astral-sh/setup-uv@v7
38
+ with:
39
+ enable-cache: true
40
+ python-version: ${{ matrix.python-version }}
41
+
42
+ - name: Install dependencies
43
+ run: |
44
+ uv sync --locked --all-groups --extra all
45
+ echo "/tmp/agilerl-venv/bin" >> $GITHUB_PATH
46
+ uv cache clean
47
+ rm -rf /tmp/uv-cache
48
+
49
+ - name: Test with pytest
50
+ run: |
51
+ uv run pytest --exitfirst --cov=agilerl --cov-report=xml
52
+
53
+ - name: Upload coverage reports to Codecov
54
+ uses: codecov/codecov-action@v3
55
+ env:
56
+ CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
@@ -106,10 +106,8 @@ celerybeat.pid
106
106
  # Environments
107
107
  .env
108
108
  .vscode/
109
- .venv
110
- # env/
109
+ .venv*/
111
110
  venv/
112
- # ENV/
113
111
  env.bak/
114
112
  venv.bak/
115
113
 
@@ -23,10 +23,6 @@ repos:
23
23
  - id: debug-statements
24
24
  - id: mixed-line-ending
25
25
  args: [--fix=lf]
26
- - repo: https://github.com/psf/black-pre-commit-mirror
27
- rev: 26.1.0
28
- hooks:
29
- - id: black
30
26
  - repo: https://github.com/codespell-project/codespell
31
27
  rev: v2.4.1
32
28
  hooks:
@@ -35,24 +31,20 @@ repos:
35
31
  - --skip=*.css,*.js,*.map,*.scss,*.svg
36
32
  - --ignore-words-list=magent,pres,roate
37
33
  - repo: https://github.com/astral-sh/ruff-pre-commit
38
- rev: v0.14.14
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
34
+ rev: v0.15.1
47
35
  hooks:
48
- - id: pyupgrade
49
- args: [--py38-plus]
36
+ - id: ruff
37
+ name: Ruff Linter
38
+ args: [--fix]
39
+ - id: ruff-format
40
+ name: Ruff Formatter
41
+
50
42
  - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt
51
43
  rev: 0.2.3
52
44
  hooks:
53
45
  - id: yamlfmt
54
46
  - repo: https://github.com/astral-sh/uv-pre-commit
55
47
  # uv version.
56
- rev: 0.9.28
48
+ rev: 0.10.2
57
49
  hooks:
58
50
  - id: uv-lock
@@ -1,23 +1,23 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: agilerl
3
- Version: 2.4.3.dev0
3
+ Version: 2.5.0.dev0
4
4
  Summary: AgileRL is a deep reinforcement learning library focused on improving RL development through RLOps.
5
5
  Author-email: Nick Ustaran-Anderegg <dev@agilerl.com>
6
6
  License-Expression: Apache-2.0
7
7
  License-File: LICENSE
8
- Requires-Python: <3.13,>=3.10
8
+ Requires-Python: <3.14,>=3.10
9
9
  Requires-Dist: accelerate~=1.7.0
10
10
  Requires-Dist: dill~=0.3.7
11
11
  Requires-Dist: fastrand~=1.3.0
12
12
  Requires-Dist: flatten-dict~=0.4.2
13
13
  Requires-Dist: google-cloud-storage~=2.5.0
14
14
  Requires-Dist: gymnasium~=1.0.0
15
- Requires-Dist: h5py~=3.8.0
15
+ Requires-Dist: h5py~=3.15.0
16
16
  Requires-Dist: hydra-core~=1.3.2
17
17
  Requires-Dist: jax[cpu]~=0.4.31
18
18
  Requires-Dist: matplotlib<3.10,~=3.9.4
19
19
  Requires-Dist: minari[all]==0.5.2
20
- Requires-Dist: numpy~=1.26.4
20
+ Requires-Dist: numpy<3.0,>=2.0.0
21
21
  Requires-Dist: omegaconf~=2.3.0
22
22
  Requires-Dist: packaging>=20.0
23
23
  Requires-Dist: pandas~=2.2.3
@@ -26,14 +26,12 @@ Requires-Dist: pre-commit~=3.8.0
26
26
  Requires-Dist: pygame~=2.6.0
27
27
  Requires-Dist: pymunk~=6.2.0
28
28
  Requires-Dist: redis~=4.4.4
29
- Requires-Dist: scipy~=1.12.0
30
29
  Requires-Dist: supersuit~=3.9.0
31
30
  Requires-Dist: tensordict~=0.8
32
31
  Requires-Dist: termcolor~=1.1.0
33
32
  Requires-Dist: torch==2.7.1
34
- Requires-Dist: tqdm~=4.66.4
35
- Requires-Dist: ucimlrepo~=0.0.3
36
- Requires-Dist: wandb~=0.17.6
33
+ Requires-Dist: tqdm>=4.66.4
34
+ Requires-Dist: wandb~=0.18.0
37
35
  Provides-Extra: all
38
36
  Requires-Dist: datasets==4.4.1; extra == 'all'
39
37
  Requires-Dist: deepspeed~=0.17.1; extra == 'all'
@@ -57,6 +55,7 @@ Description-Content-Type: text/markdown
57
55
 
58
56
  [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
59
57
  [![Documentation Status](https://readthedocs.org/projects/agilerl/badge/?version=latest)](https://docs.agilerl.com/en/latest/?badge=latest)
58
+ [![Tests](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml/badge.svg)](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml)
60
59
  [![Downloads](https://static.pepy.tech/badge/agilerl)](https://pypi.python.org/pypi/agilerl/)
61
60
  [![Discord](https://dcbadge.limes.pink/api/server/https://discord.gg/eB8HyTA2ux?style=flat)](https://discord.gg/eB8HyTA2ux)
62
61
  [![Arena](./.github/badges/arena-github-badge.svg)](https://arena.agilerl.com)
@@ -7,6 +7,7 @@
7
7
 
8
8
  [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
9
9
  [![Documentation Status](https://readthedocs.org/projects/agilerl/badge/?version=latest)](https://docs.agilerl.com/en/latest/?badge=latest)
10
+ [![Tests](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml/badge.svg)](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml)
10
11
  [![Downloads](https://static.pepy.tech/badge/agilerl)](https://pypi.python.org/pypi/agilerl/)
11
12
  [![Discord](https://dcbadge.limes.pink/api/server/https://discord.gg/eB8HyTA2ux?style=flat)](https://discord.gg/eB8HyTA2ux)
12
13
  [![Arena](./.github/badges/arena-github-badge.svg)](https://arena.agilerl.com)