agilerl 2.7.0.dev2__tar.gz → 2.8.0.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 (485) hide show
  1. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/.gitignore +11 -0
  2. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/PKG-INFO +341 -229
  3. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/README.md +292 -186
  4. agilerl-2.8.0.dev0/agilerl/__init__.py +77 -0
  5. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/cispo.py +1 -4
  6. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/core/__init__.py +8 -1
  7. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/core/base.py +1903 -694
  8. agilerl-2.8.0.dev0/agilerl/algorithms/core/llm_ops/__init__.py +49 -0
  9. agilerl-2.8.0.dev0/agilerl/algorithms/core/llm_ops/fused_logprobs.py +274 -0
  10. agilerl-2.8.0.dev0/agilerl/algorithms/core/llm_ops/fused_lora.py +271 -0
  11. agilerl-2.8.0.dev0/agilerl/algorithms/core/llm_ops/fused_loss.py +769 -0
  12. agilerl-2.8.0.dev0/agilerl/algorithms/core/llm_ops/vllm_colocate.py +201 -0
  13. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/core/registry.py +27 -2
  14. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/cqn.py +37 -19
  15. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/ddpg.py +34 -21
  16. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/dpo.py +102 -19
  17. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/dqn.py +50 -27
  18. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/dqn_rainbow.py +38 -19
  19. agilerl-2.8.0.dev0/agilerl/algorithms/grpo.py +1876 -0
  20. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/gspo.py +1 -4
  21. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/ilql.py +3 -1
  22. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/ippo.py +65 -35
  23. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/maddpg.py +46 -28
  24. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/matd3.py +51 -29
  25. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/neural_ts_bandit.py +37 -20
  26. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/neural_ucb_bandit.py +39 -24
  27. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/ppo.py +112 -251
  28. agilerl-2.8.0.dev0/agilerl/algorithms/ppo_llm.py +1496 -0
  29. agilerl-2.8.0.dev0/agilerl/algorithms/reinforce_llm.py +1206 -0
  30. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/sft.py +97 -30
  31. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/td3.py +42 -20
  32. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/__init__.py +0 -2
  33. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/data.py +50 -1
  34. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/replay_buffer.py +98 -51
  35. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/rollout_buffer.py +2 -7
  36. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/sampler.py +5 -10
  37. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/components/segment_tree.py +65 -5
  38. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/hpo/mutation.py +4 -4
  39. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/hpo/tournament.py +33 -22
  40. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/preference.py +19 -1
  41. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/reasoning.py +19 -1
  42. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/sft.py +43 -5
  43. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/sync_vec_env.py +60 -8
  44. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/token_observation.py +156 -19
  45. agilerl-2.8.0.dev0/agilerl/logger.py +253 -0
  46. agilerl-2.8.0.dev0/agilerl/metrics.py +374 -0
  47. agilerl-2.8.0.dev0/agilerl/models/__init__.py +82 -0
  48. agilerl-2.8.0.dev0/agilerl/models/algo.py +596 -0
  49. agilerl-2.8.0.dev0/agilerl/models/algorithms/__init__.py +54 -0
  50. agilerl-2.8.0.dev0/agilerl/models/algorithms/cispo.py +35 -0
  51. agilerl-2.8.0.dev0/agilerl/models/algorithms/cqn.py +41 -0
  52. agilerl-2.8.0.dev0/agilerl/models/algorithms/ddpg.py +48 -0
  53. agilerl-2.8.0.dev0/agilerl/models/algorithms/dpo.py +33 -0
  54. agilerl-2.8.0.dev0/agilerl/models/algorithms/dqn.py +40 -0
  55. agilerl-2.8.0.dev0/agilerl/models/algorithms/grpo.py +66 -0
  56. agilerl-2.8.0.dev0/agilerl/models/algorithms/gspo.py +30 -0
  57. agilerl-2.8.0.dev0/agilerl/models/algorithms/ippo.py +50 -0
  58. agilerl-2.8.0.dev0/agilerl/models/algorithms/llmppo.py +68 -0
  59. agilerl-2.8.0.dev0/agilerl/models/algorithms/llmreinforce.py +63 -0
  60. agilerl-2.8.0.dev0/agilerl/models/algorithms/maddpg.py +49 -0
  61. agilerl-2.8.0.dev0/agilerl/models/algorithms/matd3.py +50 -0
  62. agilerl-2.8.0.dev0/agilerl/models/algorithms/neural_ts.py +43 -0
  63. agilerl-2.8.0.dev0/agilerl/models/algorithms/neural_ucb.py +43 -0
  64. agilerl-2.8.0.dev0/agilerl/models/algorithms/ppo.py +59 -0
  65. agilerl-2.8.0.dev0/agilerl/models/algorithms/rainbow_dqn.py +54 -0
  66. agilerl-2.8.0.dev0/agilerl/models/algorithms/sft.py +33 -0
  67. agilerl-2.8.0.dev0/agilerl/models/algorithms/td3.py +48 -0
  68. agilerl-2.8.0.dev0/agilerl/models/env.py +851 -0
  69. agilerl-2.8.0.dev0/agilerl/models/hpo.py +81 -0
  70. agilerl-2.8.0.dev0/agilerl/models/manifest.py +370 -0
  71. agilerl-2.8.0.dev0/agilerl/models/networks.py +456 -0
  72. agilerl-2.8.0.dev0/agilerl/models/training.py +255 -0
  73. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/base.py +4 -4
  74. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/cnn.py +11 -0
  75. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/actors.py +14 -15
  76. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/base.py +1 -1
  77. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/q_networks.py +6 -6
  78. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/value_networks.py +2 -2
  79. agilerl-2.8.0.dev0/agilerl/population.py +738 -0
  80. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/protocols.py +40 -3
  81. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/rollouts/on_policy.py +17 -14
  82. agilerl-2.8.0.dev0/agilerl/train.py +159 -0
  83. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/training/train_bandits.py +95 -169
  84. agilerl-2.8.0.dev0/agilerl/training/train_llm.py +1205 -0
  85. agilerl-2.8.0.dev0/agilerl/training/train_multi_agent_off_policy.py +375 -0
  86. agilerl-2.8.0.dev0/agilerl/training/train_multi_agent_on_policy.py +394 -0
  87. agilerl-2.8.0.dev0/agilerl/training/train_off_policy.py +448 -0
  88. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/training/train_offline.py +106 -156
  89. agilerl-2.8.0.dev0/agilerl/training/train_on_policy.py +292 -0
  90. agilerl-2.8.0.dev0/agilerl/training/trainer.py +731 -0
  91. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/typing.py +19 -3
  92. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/algo_utils.py +264 -34
  93. agilerl-2.8.0.dev0/agilerl/utils/env_utils.py +260 -0
  94. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/evolvable_networks.py +1 -1
  95. agilerl-2.8.0.dev0/agilerl/utils/llm_packing.py +276 -0
  96. agilerl-2.8.0.dev0/agilerl/utils/llm_utils.py +2041 -0
  97. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/minari_utils.py +36 -6
  98. agilerl-2.8.0.dev0/agilerl/utils/population_utils.py +212 -0
  99. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/ppo_value_head.py +7 -3
  100. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/probe_envs.py +3 -48
  101. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/probe_envs_ma.py +15 -10
  102. agilerl-2.8.0.dev0/agilerl/utils/trainer_utils.py +324 -0
  103. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/utils.py +236 -136
  104. agilerl-2.8.0.dev0/agilerl/vector/__init__.py +10 -0
  105. agilerl-2.8.0.dev0/agilerl/vector/dummy_vec_env.py +339 -0
  106. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/vector/pz_vec_env.py +1 -0
  107. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/agent.py +114 -96
  108. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/learning.py +63 -14
  109. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/pettingzoo_wrappers.py +60 -1
  110. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/pyproject.toml +97 -58
  111. agilerl-2.7.0.dev2/.github/ISSUE_TEMPLATE/bug_report.md +0 -27
  112. agilerl-2.7.0.dev2/.github/ISSUE_TEMPLATE/feature_request.md +0 -20
  113. agilerl-2.7.0.dev2/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md +0 -34
  114. agilerl-2.7.0.dev2/.github/badges/arena-github-badge.svg +0 -24
  115. agilerl-2.7.0.dev2/.github/codeql/install_codeql.sh +0 -51
  116. agilerl-2.7.0.dev2/.github/codeql/run_codeql.py +0 -139
  117. agilerl-2.7.0.dev2/.github/dependabot.yml +0 -8
  118. agilerl-2.7.0.dev2/.github/workflows/codeql.yml +0 -101
  119. agilerl-2.7.0.dev2/.github/workflows/linux-tests.yml +0 -94
  120. agilerl-2.7.0.dev2/.github/workflows/macos-tests.yml +0 -50
  121. agilerl-2.7.0.dev2/.github/workflows/windows-tests.yml +0 -51
  122. agilerl-2.7.0.dev2/.pre-commit-config.yaml +0 -65
  123. agilerl-2.7.0.dev2/.readthedocs.yaml +0 -30
  124. agilerl-2.7.0.dev2/CITATION.cff +0 -20
  125. agilerl-2.7.0.dev2/CODE_OF_CONDUCT.md +0 -128
  126. agilerl-2.7.0.dev2/CONTRIBUTING.md +0 -73
  127. agilerl-2.7.0.dev2/agilerl/__init__.py +0 -47
  128. agilerl-2.7.0.dev2/agilerl/algorithms/core/fused_lora.py +0 -146
  129. agilerl-2.7.0.dev2/agilerl/algorithms/grpo.py +0 -1076
  130. agilerl-2.7.0.dev2/agilerl/algorithms/ppo_llm.py +0 -905
  131. agilerl-2.7.0.dev2/agilerl/algorithms/reinforce_llm.py +0 -729
  132. agilerl-2.7.0.dev2/agilerl/components/multi_agent_replay_buffer.py +0 -242
  133. agilerl-2.7.0.dev2/agilerl/training/train_llm.py +0 -1867
  134. agilerl-2.7.0.dev2/agilerl/training/train_multi_agent_off_policy.py +0 -612
  135. agilerl-2.7.0.dev2/agilerl/training/train_multi_agent_on_policy.py +0 -623
  136. agilerl-2.7.0.dev2/agilerl/training/train_off_policy.py +0 -616
  137. agilerl-2.7.0.dev2/agilerl/training/train_on_policy.py +0 -511
  138. agilerl-2.7.0.dev2/agilerl/utils/llm_utils.py +0 -867
  139. agilerl-2.7.0.dev2/agilerl/wrappers/__init__.py +0 -0
  140. agilerl-2.7.0.dev2/benchmarking/benchmarking_bandits.py +0 -146
  141. agilerl-2.7.0.dev2/benchmarking/benchmarking_llm_multiturn.py +0 -120
  142. agilerl-2.7.0.dev2/benchmarking/benchmarking_llm_preference.py +0 -176
  143. agilerl-2.7.0.dev2/benchmarking/benchmarking_llm_reasoning.py +0 -198
  144. agilerl-2.7.0.dev2/benchmarking/benchmarking_multi_agent_off_policy.py +0 -224
  145. agilerl-2.7.0.dev2/benchmarking/benchmarking_multi_agent_on_policy.py +0 -169
  146. agilerl-2.7.0.dev2/benchmarking/benchmarking_off_policy.py +0 -179
  147. agilerl-2.7.0.dev2/benchmarking/benchmarking_off_policy_distributed.py +0 -107
  148. agilerl-2.7.0.dev2/benchmarking/benchmarking_offline.py +0 -148
  149. agilerl-2.7.0.dev2/benchmarking/benchmarking_offline_distributed.py +0 -144
  150. agilerl-2.7.0.dev2/benchmarking/benchmarking_on_policy.py +0 -118
  151. agilerl-2.7.0.dev2/benchmarking/benchmarking_rainbow.py +0 -175
  152. agilerl-2.7.0.dev2/benchmarking/benchmarking_recurrent.py +0 -176
  153. agilerl-2.7.0.dev2/benchmarking/benchmarking_resnet.py +0 -110
  154. agilerl-2.7.0.dev2/benchmarking/benchmarking_sft.py +0 -172
  155. agilerl-2.7.0.dev2/benchmarking/benchmarking_simba.py +0 -131
  156. agilerl-2.7.0.dev2/benchmarking/configs/ds_config.json +0 -16
  157. agilerl-2.7.0.dev2/benchmarking/make_evolvable_benchmarking.py +0 -490
  158. agilerl-2.7.0.dev2/benchmarking/networks.py +0 -569
  159. agilerl-2.7.0.dev2/configs/accelerate/accelerate.yaml +0 -13
  160. agilerl-2.7.0.dev2/configs/accelerate/grpo_accelerate_config.yaml +0 -25
  161. agilerl-2.7.0.dev2/configs/training/bandit/neural_ts.yaml +0 -53
  162. agilerl-2.7.0.dev2/configs/training/bandit/neural_ucb.yaml +0 -53
  163. agilerl-2.7.0.dev2/configs/training/cqn.yaml +0 -55
  164. agilerl-2.7.0.dev2/configs/training/ddpg/ddpg.yaml +0 -70
  165. agilerl-2.7.0.dev2/configs/training/ddpg/ddpg_lstm.yaml +0 -69
  166. agilerl-2.7.0.dev2/configs/training/ddpg/ddpg_simba.yaml +0 -71
  167. agilerl-2.7.0.dev2/configs/training/dqn/dqn.yaml +0 -56
  168. agilerl-2.7.0.dev2/configs/training/dqn/dqn_lstm.yaml +0 -64
  169. agilerl-2.7.0.dev2/configs/training/dqn/dqn_rainbow.yaml +0 -69
  170. agilerl-2.7.0.dev2/configs/training/llm_finetuning/cispo.yaml +0 -38
  171. agilerl-2.7.0.dev2/configs/training/llm_finetuning/dpo.yaml +0 -50
  172. agilerl-2.7.0.dev2/configs/training/llm_finetuning/grpo.yaml +0 -41
  173. agilerl-2.7.0.dev2/configs/training/llm_finetuning/grpo_multiturn.yaml +0 -30
  174. agilerl-2.7.0.dev2/configs/training/llm_finetuning/gspo.yaml +0 -36
  175. agilerl-2.7.0.dev2/configs/training/llm_finetuning/ppo_llm.yaml +0 -47
  176. agilerl-2.7.0.dev2/configs/training/llm_finetuning/reinforce_llm.yaml +0 -42
  177. agilerl-2.7.0.dev2/configs/training/multi_agent/ippo.yaml +0 -78
  178. agilerl-2.7.0.dev2/configs/training/multi_agent/ippo_pong.yaml +0 -69
  179. agilerl-2.7.0.dev2/configs/training/multi_agent/maddpg.yaml +0 -94
  180. agilerl-2.7.0.dev2/configs/training/multi_agent/matd3.yaml +0 -70
  181. agilerl-2.7.0.dev2/configs/training/multi_input.yaml +0 -64
  182. agilerl-2.7.0.dev2/configs/training/ppo/ppo.yaml +0 -73
  183. agilerl-2.7.0.dev2/configs/training/ppo/ppo_image.yaml +0 -86
  184. agilerl-2.7.0.dev2/configs/training/ppo/ppo_recurrent.yaml +0 -65
  185. agilerl-2.7.0.dev2/configs/training/sft.yaml +0 -43
  186. agilerl-2.7.0.dev2/configs/training/td3.yaml +0 -64
  187. agilerl-2.7.0.dev2/data/cartpole/cartpole_random_v1.1.0.h5 +0 -0
  188. agilerl-2.7.0.dev2/data/cartpole/cartpole_v1.1.0.h5 +0 -0
  189. agilerl-2.7.0.dev2/data/pendulum/pendulum_random_v1.1.0.h5 +0 -0
  190. agilerl-2.7.0.dev2/data/pendulum/pendulum_v1.1.0.h5 +0 -0
  191. agilerl-2.7.0.dev2/demos/bandits/demo_bandit.py +0 -188
  192. agilerl-2.7.0.dev2/demos/llm/debugging/config_load.py +0 -22
  193. agilerl-2.7.0.dev2/demos/llm/debugging/configs/grpo_constant_target.yaml +0 -24
  194. agilerl-2.7.0.dev2/demos/llm/debugging/configs/grpo_grid_navigation.yaml +0 -26
  195. agilerl-2.7.0.dev2/demos/llm/debugging/configs/ppo_conditional_target.yaml +0 -31
  196. agilerl-2.7.0.dev2/demos/llm/debugging/configs/ppo_constant_target.yaml +0 -27
  197. agilerl-2.7.0.dev2/demos/llm/debugging/configs/ppo_grid_navigation.yaml +0 -29
  198. agilerl-2.7.0.dev2/demos/llm/debugging/configs/ppo_multi_input.yaml +0 -28
  199. agilerl-2.7.0.dev2/demos/llm/debugging/configs/ppo_value_head.yaml +0 -30
  200. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_llm.py +0 -186
  201. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_llm_stage_1.py +0 -252
  202. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_llm_stage_2.py +0 -283
  203. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_llm_stage_3.py +0 -400
  204. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_llm_training_matrix.py +0 -697
  205. agilerl-2.7.0.dev2/demos/llm/debugging/debugging_value.py +0 -190
  206. agilerl-2.7.0.dev2/demos/llm/debugging/llm_debug_utils.py +0 -16
  207. agilerl-2.7.0.dev2/demos/llm/debugging/tiny_model.py +0 -229
  208. agilerl-2.7.0.dev2/demos/llm/demo_llm_finetuning.py +0 -338
  209. agilerl-2.7.0.dev2/demos/multi_agent/demo_multi_agent.py +0 -253
  210. agilerl-2.7.0.dev2/demos/single_agent/demo_custom_network.py +0 -222
  211. agilerl-2.7.0.dev2/demos/single_agent/demo_off_policy.py +0 -196
  212. agilerl-2.7.0.dev2/demos/single_agent/demo_off_policy_distributed.py +0 -226
  213. agilerl-2.7.0.dev2/demos/single_agent/demo_offline.py +0 -147
  214. agilerl-2.7.0.dev2/demos/single_agent/demo_offline_distributed.py +0 -188
  215. agilerl-2.7.0.dev2/demos/single_agent/demo_on_policy.py +0 -155
  216. agilerl-2.7.0.dev2/demos/single_agent/demo_on_policy_rnn_cartpole.py +0 -276
  217. agilerl-2.7.0.dev2/demos/single_agent/demo_on_policy_rnn_memory.py +0 -348
  218. agilerl-2.7.0.dev2/demos/single_agent/demo_on_policy_rnn_minigrid.py +0 -315
  219. agilerl-2.7.0.dev2/demos/single_agent/performance_flamegraph_cartpole.py +0 -226
  220. agilerl-2.7.0.dev2/demos/single_agent/performance_flamegraph_lunar_lander.py +0 -230
  221. agilerl-2.7.0.dev2/demos/single_agent/performance_flamegraph_lunar_lander_rnn.py +0 -240
  222. agilerl-2.7.0.dev2/demos/single_agent/performance_flamegraph_rnn_memory.py +0 -280
  223. agilerl-2.7.0.dev2/docs/Makefile +0 -20
  224. agilerl-2.7.0.dev2/docs/__init__.py +0 -1
  225. agilerl-2.7.0.dev2/docs/_static/arena-github-badge.svg +0 -1
  226. agilerl-2.7.0.dev2/docs/_static/css/custom.css +0 -0
  227. agilerl-2.7.0.dev2/docs/_static/favicon.ico +0 -0
  228. agilerl-2.7.0.dev2/docs/_static/js/expand_sidebar.js +0 -6
  229. agilerl-2.7.0.dev2/docs/_static/logo_teal.png +0 -0
  230. agilerl-2.7.0.dev2/docs/_static/logo_white.png +0 -0
  231. agilerl-2.7.0.dev2/docs/_static/module.png +0 -0
  232. agilerl-2.7.0.dev2/docs/_static/network.png +0 -0
  233. agilerl-2.7.0.dev2/docs/_static/thumbnails/iris-thumbnail.png +0 -0
  234. agilerl-2.7.0.dev2/docs/_static/thumbnails/pendigits-thumbnail.png +0 -0
  235. agilerl-2.7.0.dev2/docs/_static/thumbnails/rainbow_performance.png +0 -0
  236. agilerl-2.7.0.dev2/docs/_static/thumbnails/simba_thumbnail.png +0 -0
  237. agilerl-2.7.0.dev2/docs/api/algorithms/base.rst +0 -292
  238. agilerl-2.7.0.dev2/docs/api/algorithms/cispo.rst +0 -137
  239. agilerl-2.7.0.dev2/docs/api/algorithms/cql.rst +0 -174
  240. agilerl-2.7.0.dev2/docs/api/algorithms/ddpg.rst +0 -196
  241. agilerl-2.7.0.dev2/docs/api/algorithms/dpo.rst +0 -121
  242. agilerl-2.7.0.dev2/docs/api/algorithms/dqn.rst +0 -166
  243. agilerl-2.7.0.dev2/docs/api/algorithms/dqn_rainbow.rst +0 -175
  244. agilerl-2.7.0.dev2/docs/api/algorithms/grpo.rst +0 -87
  245. agilerl-2.7.0.dev2/docs/api/algorithms/gspo.rst +0 -134
  246. agilerl-2.7.0.dev2/docs/api/algorithms/ilql.rst +0 -15
  247. agilerl-2.7.0.dev2/docs/api/algorithms/index.rst +0 -183
  248. agilerl-2.7.0.dev2/docs/api/algorithms/ippo.rst +0 -344
  249. agilerl-2.7.0.dev2/docs/api/algorithms/llmppo.rst +0 -147
  250. agilerl-2.7.0.dev2/docs/api/algorithms/llmreinforce.rst +0 -145
  251. agilerl-2.7.0.dev2/docs/api/algorithms/maddpg.rst +0 -274
  252. agilerl-2.7.0.dev2/docs/api/algorithms/matd3.rst +0 -273
  253. agilerl-2.7.0.dev2/docs/api/algorithms/neural_ts.rst +0 -154
  254. agilerl-2.7.0.dev2/docs/api/algorithms/neural_ucb.rst +0 -155
  255. agilerl-2.7.0.dev2/docs/api/algorithms/ppo.rst +0 -222
  256. agilerl-2.7.0.dev2/docs/api/algorithms/registry.rst +0 -19
  257. agilerl-2.7.0.dev2/docs/api/algorithms/sft.rst +0 -131
  258. agilerl-2.7.0.dev2/docs/api/algorithms/td3.rst +0 -185
  259. agilerl-2.7.0.dev2/docs/api/algorithms/wrappers.rst +0 -10
  260. agilerl-2.7.0.dev2/docs/api/components/data.rst +0 -46
  261. agilerl-2.7.0.dev2/docs/api/components/index.rst +0 -12
  262. agilerl-2.7.0.dev2/docs/api/components/multi_agent_replay_buffer.rst +0 -27
  263. agilerl-2.7.0.dev2/docs/api/components/replay_buffer.rst +0 -35
  264. agilerl-2.7.0.dev2/docs/api/components/rollout_buffer.rst +0 -61
  265. agilerl-2.7.0.dev2/docs/api/components/sampler.rst +0 -37
  266. agilerl-2.7.0.dev2/docs/api/components/segment_tree.rst +0 -37
  267. agilerl-2.7.0.dev2/docs/api/hpo/index.rst +0 -14
  268. agilerl-2.7.0.dev2/docs/api/hpo/mutation.rst +0 -45
  269. agilerl-2.7.0.dev2/docs/api/hpo/tournament.rst +0 -28
  270. agilerl-2.7.0.dev2/docs/api/modules/base.rst +0 -33
  271. agilerl-2.7.0.dev2/docs/api/modules/bert.rst +0 -17
  272. agilerl-2.7.0.dev2/docs/api/modules/cnn.rst +0 -10
  273. agilerl-2.7.0.dev2/docs/api/modules/custom_activation.rst +0 -7
  274. agilerl-2.7.0.dev2/docs/api/modules/dummy.rst +0 -14
  275. agilerl-2.7.0.dev2/docs/api/modules/gpt.rst +0 -26
  276. agilerl-2.7.0.dev2/docs/api/modules/index.rst +0 -26
  277. agilerl-2.7.0.dev2/docs/api/modules/lstm.rst +0 -10
  278. agilerl-2.7.0.dev2/docs/api/modules/mlp.rst +0 -10
  279. agilerl-2.7.0.dev2/docs/api/modules/multi_input.rst +0 -10
  280. agilerl-2.7.0.dev2/docs/api/modules/resnet.rst +0 -12
  281. agilerl-2.7.0.dev2/docs/api/modules/simba.rst +0 -12
  282. agilerl-2.7.0.dev2/docs/api/networks/actors.rst +0 -28
  283. agilerl-2.7.0.dev2/docs/api/networks/base.rst +0 -10
  284. agilerl-2.7.0.dev2/docs/api/networks/index.rst +0 -18
  285. agilerl-2.7.0.dev2/docs/api/networks/q_networks.rst +0 -28
  286. agilerl-2.7.0.dev2/docs/api/networks/value_networks.rst +0 -10
  287. agilerl-2.7.0.dev2/docs/api/rollouts/index.rst +0 -10
  288. agilerl-2.7.0.dev2/docs/api/rollouts/on_policy.rst +0 -42
  289. agilerl-2.7.0.dev2/docs/api/train.rst +0 -25
  290. agilerl-2.7.0.dev2/docs/api/utils/algo_utils.rst +0 -105
  291. agilerl-2.7.0.dev2/docs/api/utils/cache.rst +0 -7
  292. agilerl-2.7.0.dev2/docs/api/utils/evolvable_networks.rst +0 -65
  293. agilerl-2.7.0.dev2/docs/api/utils/ilql_utils.rst +0 -12
  294. agilerl-2.7.0.dev2/docs/api/utils/index.rst +0 -16
  295. agilerl-2.7.0.dev2/docs/api/utils/llm_utils.rst +0 -12
  296. agilerl-2.7.0.dev2/docs/api/utils/log_utils.rst +0 -9
  297. agilerl-2.7.0.dev2/docs/api/utils/minari_utils.rst +0 -8
  298. agilerl-2.7.0.dev2/docs/api/utils/probe_envs.rst +0 -386
  299. agilerl-2.7.0.dev2/docs/api/utils/torch_utils.rst +0 -12
  300. agilerl-2.7.0.dev2/docs/api/utils/utils.rst +0 -34
  301. agilerl-2.7.0.dev2/docs/api/vector/index.rst +0 -8
  302. agilerl-2.7.0.dev2/docs/api/vector/petting_zoo_async_vector_env.rst +0 -62
  303. agilerl-2.7.0.dev2/docs/api/vector/petting_zoo_vector_env.rst +0 -10
  304. agilerl-2.7.0.dev2/docs/api/wrappers/agent.rst +0 -28
  305. agilerl-2.7.0.dev2/docs/api/wrappers/index.rst +0 -11
  306. agilerl-2.7.0.dev2/docs/api/wrappers/learning.rst +0 -17
  307. agilerl-2.7.0.dev2/docs/api/wrappers/llm_envs.rst +0 -12
  308. agilerl-2.7.0.dev2/docs/api/wrappers/make_evolvable.rst +0 -8
  309. agilerl-2.7.0.dev2/docs/api/wrappers/pettingzoo.rst +0 -8
  310. agilerl-2.7.0.dev2/docs/bandits/index.rst +0 -336
  311. agilerl-2.7.0.dev2/docs/conf.py +0 -80
  312. agilerl-2.7.0.dev2/docs/custom_algorithms/index.rst +0 -75
  313. agilerl-2.7.0.dev2/docs/debugging_rl/index.rst +0 -368
  314. agilerl-2.7.0.dev2/docs/distributed_training/index.rst +0 -251
  315. agilerl-2.7.0.dev2/docs/evo_hyperparam_opt/index.rst +0 -242
  316. agilerl-2.7.0.dev2/docs/evolvable_networks/index.rst +0 -589
  317. agilerl-2.7.0.dev2/docs/get_started/agilerl2changes.rst +0 -66
  318. agilerl-2.7.0.dev2/docs/get_started/index.rst +0 -445
  319. agilerl-2.7.0.dev2/docs/index.rst +0 -148
  320. agilerl-2.7.0.dev2/docs/llm_finetuning/index.rst +0 -58
  321. agilerl-2.7.0.dev2/docs/llm_finetuning/llm_checkpoints.rst +0 -148
  322. agilerl-2.7.0.dev2/docs/make.bat +0 -35
  323. agilerl-2.7.0.dev2/docs/multi_agent_training/index.rst +0 -700
  324. agilerl-2.7.0.dev2/docs/off_policy/index.rst +0 -340
  325. agilerl-2.7.0.dev2/docs/offline_training/index.rst +0 -300
  326. agilerl-2.7.0.dev2/docs/on_policy/index.rst +0 -503
  327. agilerl-2.7.0.dev2/docs/pomdp/index.rst +0 -35
  328. agilerl-2.7.0.dev2/docs/releases/index.rst +0 -7
  329. agilerl-2.7.0.dev2/docs/requirements.txt +0 -6
  330. agilerl-2.7.0.dev2/sitecustomize.py +0 -12
  331. agilerl-2.7.0.dev2/tests/__init__.py +0 -5
  332. agilerl-2.7.0.dev2/tests/assets/build_minari_fixture.py +0 -67
  333. agilerl-2.7.0.dev2/tests/assets/build_tiny_llm_fixture.py +0 -129
  334. agilerl-2.7.0.dev2/tests/assets/minari_cache/D4RL/door/human-v2/data/main_data.hdf5 +0 -0
  335. agilerl-2.7.0.dev2/tests/assets/minari_cache/D4RL/door/human-v2/data/metadata.json +0 -1
  336. agilerl-2.7.0.dev2/tests/assets/minari_cache/D4RL/door/namespace_metadata.json +0 -1
  337. agilerl-2.7.0.dev2/tests/assets/minari_cache/D4RL/namespace_metadata.json +0 -1
  338. agilerl-2.7.0.dev2/tests/assets/tiny_llm/added_tokens.json +0 -24
  339. agilerl-2.7.0.dev2/tests/assets/tiny_llm/chat_template.jinja +0 -54
  340. agilerl-2.7.0.dev2/tests/assets/tiny_llm/config.json +0 -32
  341. agilerl-2.7.0.dev2/tests/assets/tiny_llm/generation_config.json +0 -6
  342. agilerl-2.7.0.dev2/tests/assets/tiny_llm/model.safetensors +0 -0
  343. agilerl-2.7.0.dev2/tests/assets/tiny_llm/special_tokens_map.json +0 -31
  344. agilerl-2.7.0.dev2/tests/assets/tiny_llm/tokenizer.json +0 -757444
  345. agilerl-2.7.0.dev2/tests/assets/tiny_llm/tokenizer_config.json +0 -207
  346. agilerl-2.7.0.dev2/tests/conftest.py +0 -490
  347. agilerl-2.7.0.dev2/tests/helper_functions.py +0 -356
  348. agilerl-2.7.0.dev2/tests/pz_vector_test_utils.py +0 -482
  349. agilerl-2.7.0.dev2/tests/subprocess_runner.py +0 -241
  350. agilerl-2.7.0.dev2/tests/test_algorithms/__init__.py +0 -0
  351. agilerl-2.7.0.dev2/tests/test_algorithms/conftest.py +0 -38
  352. agilerl-2.7.0.dev2/tests/test_algorithms/test_bandits/__init__.py +0 -0
  353. agilerl-2.7.0.dev2/tests/test_algorithms/test_bandits/test_neural_ts.py +0 -500
  354. agilerl-2.7.0.dev2/tests/test_algorithms/test_bandits/test_neural_ucb.py +0 -517
  355. agilerl-2.7.0.dev2/tests/test_algorithms/test_base.py +0 -1679
  356. agilerl-2.7.0.dev2/tests/test_algorithms/test_bc_lm.py +0 -1234
  357. agilerl-2.7.0.dev2/tests/test_algorithms/test_core_base.py +0 -5482
  358. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/__init__.py +0 -0
  359. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/conftest.py +0 -116
  360. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_dpo.py +0 -907
  361. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_fused_lora.py +0 -125
  362. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_grpo.py +0 -4859
  363. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_llm_checkpoint.py +0 -0
  364. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_ppo_llm.py +0 -1094
  365. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_reinforce_llm.py +0 -962
  366. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_sft.py +0 -917
  367. agilerl-2.7.0.dev2/tests/test_algorithms/test_llms/test_vllm.py +0 -143
  368. agilerl-2.7.0.dev2/tests/test_algorithms/test_multi_agent/__init__.py +0 -0
  369. agilerl-2.7.0.dev2/tests/test_algorithms/test_multi_agent/conftest.py +0 -41
  370. agilerl-2.7.0.dev2/tests/test_algorithms/test_multi_agent/test_ippo.py +0 -2199
  371. agilerl-2.7.0.dev2/tests/test_algorithms/test_multi_agent/test_maddpg.py +0 -1813
  372. agilerl-2.7.0.dev2/tests/test_algorithms/test_multi_agent/test_matd3.py +0 -1972
  373. agilerl-2.7.0.dev2/tests/test_algorithms/test_optimizer_wrapper.py +0 -1543
  374. agilerl-2.7.0.dev2/tests/test_algorithms/test_registry.py +0 -1119
  375. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/__init__.py +0 -0
  376. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_cqn.py +0 -573
  377. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_ddpg.py +0 -834
  378. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_dqn.py +0 -598
  379. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_dqn_rainbow.py +0 -799
  380. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_ilql.py +0 -1147
  381. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_ppo.py +0 -2073
  382. agilerl-2.7.0.dev2/tests/test_algorithms/test_single_agent/test_td3.py +0 -1070
  383. agilerl-2.7.0.dev2/tests/test_components/__init__.py +0 -0
  384. agilerl-2.7.0.dev2/tests/test_components/test_multi_agent_replay_buffer.py +0 -638
  385. agilerl-2.7.0.dev2/tests/test_components/test_replay_buffer.py +0 -1056
  386. agilerl-2.7.0.dev2/tests/test_components/test_replay_data.py +0 -170
  387. agilerl-2.7.0.dev2/tests/test_components/test_rollout_buffer.py +0 -2097
  388. agilerl-2.7.0.dev2/tests/test_components/test_sampler.py +0 -487
  389. agilerl-2.7.0.dev2/tests/test_components/test_segment_tree.py +0 -129
  390. agilerl-2.7.0.dev2/tests/test_data.py +0 -456
  391. agilerl-2.7.0.dev2/tests/test_hpo/__init__.py +0 -0
  392. agilerl-2.7.0.dev2/tests/test_hpo/test_mutation.py +0 -2191
  393. agilerl-2.7.0.dev2/tests/test_hpo/test_tournament.py +0 -523
  394. agilerl-2.7.0.dev2/tests/test_init.py +0 -25
  395. agilerl-2.7.0.dev2/tests/test_modules/__init__.py +0 -0
  396. agilerl-2.7.0.dev2/tests/test_modules/test_base.py +0 -957
  397. agilerl-2.7.0.dev2/tests/test_modules/test_bert.py +0 -380
  398. agilerl-2.7.0.dev2/tests/test_modules/test_cnn.py +0 -990
  399. agilerl-2.7.0.dev2/tests/test_modules/test_configs.py +0 -85
  400. agilerl-2.7.0.dev2/tests/test_modules/test_custom_activation.py +0 -26
  401. agilerl-2.7.0.dev2/tests/test_modules/test_dummy.py +0 -77
  402. agilerl-2.7.0.dev2/tests/test_modules/test_gpt.py +0 -416
  403. agilerl-2.7.0.dev2/tests/test_modules/test_lstm.py +0 -494
  404. agilerl-2.7.0.dev2/tests/test_modules/test_mlp.py +0 -291
  405. agilerl-2.7.0.dev2/tests/test_modules/test_multi_input.py +0 -1103
  406. agilerl-2.7.0.dev2/tests/test_modules/test_resnet.py +0 -386
  407. agilerl-2.7.0.dev2/tests/test_modules/test_simba.py +0 -357
  408. agilerl-2.7.0.dev2/tests/test_networks/__init__.py +0 -0
  409. agilerl-2.7.0.dev2/tests/test_networks/test_actors.py +0 -854
  410. agilerl-2.7.0.dev2/tests/test_networks/test_base.py +0 -550
  411. agilerl-2.7.0.dev2/tests/test_networks/test_distributions.py +0 -279
  412. agilerl-2.7.0.dev2/tests/test_networks/test_q_networks.py +0 -638
  413. agilerl-2.7.0.dev2/tests/test_networks/test_value_functions.py +0 -190
  414. agilerl-2.7.0.dev2/tests/test_protocols.py +0 -565
  415. agilerl-2.7.0.dev2/tests/test_rollouts/test_on_policy.py +0 -393
  416. agilerl-2.7.0.dev2/tests/test_train/test_train.py +0 -5482
  417. agilerl-2.7.0.dev2/tests/test_train/test_train_llm.py +0 -2771
  418. agilerl-2.7.0.dev2/tests/test_utils/__init__.py +0 -0
  419. agilerl-2.7.0.dev2/tests/test_utils/test_algo_utils.py +0 -1951
  420. agilerl-2.7.0.dev2/tests/test_utils/test_cache.py +0 -62
  421. agilerl-2.7.0.dev2/tests/test_utils/test_ilql_utils.py +0 -82
  422. agilerl-2.7.0.dev2/tests/test_utils/test_llm_utils.py +0 -1284
  423. agilerl-2.7.0.dev2/tests/test_utils/test_log_utils.py +0 -213
  424. agilerl-2.7.0.dev2/tests/test_utils/test_minari_utils.py +0 -307
  425. agilerl-2.7.0.dev2/tests/test_utils/test_ppo_value_head.py +0 -482
  426. agilerl-2.7.0.dev2/tests/test_utils/test_probe_envs.py +0 -740
  427. agilerl-2.7.0.dev2/tests/test_utils/test_probe_envs_llm.py +0 -268
  428. agilerl-2.7.0.dev2/tests/test_utils/test_probe_envs_ma.py +0 -803
  429. agilerl-2.7.0.dev2/tests/test_utils/test_sampling_utils.py +0 -175
  430. agilerl-2.7.0.dev2/tests/test_utils/test_torch_utils.py +0 -317
  431. agilerl-2.7.0.dev2/tests/test_utils/test_utils.py +0 -1204
  432. agilerl-2.7.0.dev2/tests/test_utils/test_utils_evolvable.py +0 -782
  433. agilerl-2.7.0.dev2/tests/test_vector/test_vector.py +0 -1758
  434. agilerl-2.7.0.dev2/tests/test_wrappers/__init__.py +0 -0
  435. agilerl-2.7.0.dev2/tests/test_wrappers/test_agent.py +0 -1549
  436. agilerl-2.7.0.dev2/tests/test_wrappers/test_autoreset.py +0 -278
  437. agilerl-2.7.0.dev2/tests/test_wrappers/test_bandit_env.py +0 -50
  438. agilerl-2.7.0.dev2/tests/test_wrappers/test_llm_envs.py +0 -1186
  439. agilerl-2.7.0.dev2/tests/test_wrappers/test_make_evolvable.py +0 -1309
  440. agilerl-2.7.0.dev2/tests/test_wrappers/test_multiturn_wrappers.py +0 -872
  441. agilerl-2.7.0.dev2/tests/test_wrappers/test_ppo_test_method.py +0 -79
  442. agilerl-2.7.0.dev2/tests/test_wrappers/test_skills.py +0 -62
  443. agilerl-2.7.0.dev2/tests/utils.py +0 -373
  444. agilerl-2.7.0.dev2/uv.lock +0 -7127
  445. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/LICENSE +0 -0
  446. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/__init__.py +0 -0
  447. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/bc_lm.py +0 -0
  448. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/algorithms/core/optimizer_wrapper.py +0 -0
  449. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/data/__init__.py +0 -0
  450. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/data/language_environment.py +0 -0
  451. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/data/rl_data.py +0 -0
  452. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/data/tokenizer.py +0 -0
  453. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/data/torch_datasets.py +0 -0
  454. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/hpo/__init__.py +0 -0
  455. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/__init__.py +0 -0
  456. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/base.py +0 -0
  457. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/llm_envs/search.py +0 -0
  458. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/__init__.py +0 -0
  459. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/bert.py +0 -0
  460. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/configs.py +0 -0
  461. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/custom_components.py +0 -0
  462. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/dummy.py +0 -0
  463. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/gpt.py +0 -0
  464. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/lstm.py +0 -0
  465. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/mlp.py +0 -0
  466. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/multi_input.py +0 -0
  467. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/resnet.py +0 -0
  468. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/modules/simba.py +0 -0
  469. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/__init__.py +0 -0
  470. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/custom_modules.py +0 -0
  471. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/networks/distributions.py +0 -0
  472. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/rollouts/__init__.py +0 -0
  473. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/training/__init__.py +0 -0
  474. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/__init__.py +0 -0
  475. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/cache.py +0 -0
  476. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/ilql_utils.py +0 -0
  477. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/log_utils.py +0 -0
  478. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/probe_envs_llm.py +0 -0
  479. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/sampling_utils.py +0 -0
  480. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/utils/torch_utils.py +0 -0
  481. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/vector/pz_async_vec_env.py +0 -0
  482. {agilerl-2.7.0.dev2/agilerl/vector → agilerl-2.8.0.dev0/agilerl/wrappers}/__init__.py +0 -0
  483. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/llm_envs.py +0 -0
  484. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/make_evolvable.py +0 -0
  485. {agilerl-2.7.0.dev2 → agilerl-2.8.0.dev0}/agilerl/wrappers/utils.py +0 -0
@@ -1,3 +1,6 @@
1
+ # Symlink for Pylance/Pyright type checking of namespace package
2
+ agilerl/arena
3
+
1
4
  # Byte-compiled / optimized / DLL files
2
5
  __pycache__/
3
6
  *.py[cod]
@@ -113,8 +116,10 @@ celerybeat.pid
113
116
  .claude/
114
117
  .venv*/
115
118
  venv/
119
+ .envrc
116
120
  env.bak/
117
121
  venv.bak/
122
+ .cursor/
118
123
 
119
124
  # Spyder project settings
120
125
  .spyderproject
@@ -136,6 +141,7 @@ dmypy.json
136
141
 
137
142
  # Saved models
138
143
  outputs/
144
+ tensorboard_logs/
139
145
 
140
146
  # Ruff
141
147
  .ruff_cache/
@@ -143,6 +149,8 @@ outputs/
143
149
  # Large data files
144
150
  data/wordle/
145
151
  data/wordle.zip
152
+ *.tar.gz
153
+ *metrics.csv
146
154
 
147
155
  # WandB
148
156
  wandb/
@@ -153,3 +161,6 @@ wandb/
153
161
  # AI assistant instructions
154
162
  CLAUDE.md
155
163
  AGENTS.md
164
+
165
+ # Simlink for type-checking
166
+ agilerl/arena/