agilerl 2.8.0.dev1__tar.gz → 2.8.0.dev2__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.
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/.gitignore +11 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/PKG-INFO +307 -197
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/README.md +298 -195
- agilerl-2.8.0.dev2/agilerl/__init__.py +77 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/base.py +296 -81
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/registry.py +27 -2
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/cqn.py +37 -19
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/ddpg.py +34 -21
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/dpo.py +40 -13
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/dqn.py +48 -25
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/dqn_rainbow.py +36 -19
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/grpo.py +29 -16
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/ilql.py +3 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/ippo.py +65 -35
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/maddpg.py +46 -28
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/matd3.py +51 -29
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/neural_ts_bandit.py +52 -24
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/neural_ucb_bandit.py +54 -28
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/ppo.py +114 -252
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/ppo_llm.py +54 -22
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/reinforce_llm.py +38 -21
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/sft.py +21 -9
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/td3.py +42 -20
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/__init__.py +0 -2
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/data.py +50 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/replay_buffer.py +98 -51
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/rollout_buffer.py +2 -7
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/sampler.py +4 -10
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/components/segment_tree.py +65 -5
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/hpo/mutation.py +4 -4
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/hpo/tournament.py +33 -22
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/preference.py +19 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/reasoning.py +19 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/sft.py +42 -4
- agilerl-2.8.0.dev2/agilerl/logger.py +253 -0
- agilerl-2.8.0.dev2/agilerl/metrics.py +374 -0
- agilerl-2.8.0.dev2/agilerl/models/__init__.py +82 -0
- agilerl-2.8.0.dev2/agilerl/models/algo.py +596 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/__init__.py +54 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/cispo.py +35 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/cqn.py +41 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/ddpg.py +48 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/dpo.py +33 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/dqn.py +40 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/grpo.py +66 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/gspo.py +30 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/ippo.py +50 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/llmppo.py +68 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/llmreinforce.py +63 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/maddpg.py +49 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/matd3.py +50 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/neural_ts.py +43 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/neural_ucb.py +43 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/ppo.py +59 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/rainbow_dqn.py +54 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/sft.py +33 -0
- agilerl-2.8.0.dev2/agilerl/models/algorithms/td3.py +48 -0
- agilerl-2.8.0.dev2/agilerl/models/env.py +851 -0
- agilerl-2.8.0.dev2/agilerl/models/hpo.py +81 -0
- agilerl-2.8.0.dev2/agilerl/models/manifest.py +470 -0
- agilerl-2.8.0.dev2/agilerl/models/networks.py +515 -0
- agilerl-2.8.0.dev2/agilerl/models/training.py +255 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/actors.py +14 -15
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/base.py +1 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/q_networks.py +6 -6
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/value_networks.py +2 -2
- agilerl-2.8.0.dev2/agilerl/population.py +738 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/protocols.py +32 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/rollouts/on_policy.py +0 -6
- agilerl-2.8.0.dev2/agilerl/train.py +159 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/training/train_bandits.py +95 -169
- agilerl-2.8.0.dev2/agilerl/training/train_llm.py +1205 -0
- agilerl-2.8.0.dev2/agilerl/training/train_multi_agent_off_policy.py +375 -0
- agilerl-2.8.0.dev2/agilerl/training/train_multi_agent_on_policy.py +394 -0
- agilerl-2.8.0.dev2/agilerl/training/train_off_policy.py +448 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/training/train_offline.py +106 -156
- agilerl-2.8.0.dev2/agilerl/training/train_on_policy.py +292 -0
- agilerl-2.8.0.dev2/agilerl/training/trainer.py +898 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/typing.py +3 -3
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/algo_utils.py +165 -37
- agilerl-2.8.0.dev2/agilerl/utils/env_utils.py +260 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/evolvable_networks.py +4 -4
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/llm_utils.py +81 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/minari_utils.py +26 -6
- agilerl-2.8.0.dev2/agilerl/utils/population_utils.py +212 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/probe_envs.py +3 -48
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/probe_envs_ma.py +15 -10
- agilerl-2.8.0.dev2/agilerl/utils/trainer_utils.py +324 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/utils.py +130 -127
- agilerl-2.8.0.dev2/agilerl/vector/__init__.py +10 -0
- agilerl-2.8.0.dev2/agilerl/vector/dummy_vec_env.py +339 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/agent.py +110 -114
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/learning.py +62 -13
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/pettingzoo_wrappers.py +60 -1
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/pyproject.toml +29 -7
- agilerl-2.8.0.dev1/.gitattributes +0 -3
- agilerl-2.8.0.dev1/.github/ISSUE_TEMPLATE/bug_report.md +0 -27
- agilerl-2.8.0.dev1/.github/ISSUE_TEMPLATE/feature_request.md +0 -20
- agilerl-2.8.0.dev1/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md +0 -34
- agilerl-2.8.0.dev1/.github/badges/arena-github-badge.svg +0 -24
- agilerl-2.8.0.dev1/.github/codeql/install_codeql.sh +0 -51
- agilerl-2.8.0.dev1/.github/codeql/run_codeql.py +0 -139
- agilerl-2.8.0.dev1/.github/dependabot.yml +0 -8
- agilerl-2.8.0.dev1/.github/workflows/codeql.yml +0 -101
- agilerl-2.8.0.dev1/.github/workflows/linux-tests.yml +0 -94
- agilerl-2.8.0.dev1/.github/workflows/macos-tests.yml +0 -50
- agilerl-2.8.0.dev1/.github/workflows/windows-tests.yml +0 -51
- agilerl-2.8.0.dev1/.pre-commit-config.yaml +0 -65
- agilerl-2.8.0.dev1/.readthedocs.yaml +0 -30
- agilerl-2.8.0.dev1/CITATION.cff +0 -20
- agilerl-2.8.0.dev1/CODE_OF_CONDUCT.md +0 -128
- agilerl-2.8.0.dev1/CONTRIBUTING.md +0 -73
- agilerl-2.8.0.dev1/DQN_LEARNING_ALGORITHM_ANALYSIS.md +0 -309
- agilerl-2.8.0.dev1/DQN_LEARNING_ANALYSIS.md +0 -168
- agilerl-2.8.0.dev1/GPU_CLEANUP_ANALYSIS.md +0 -541
- agilerl-2.8.0.dev1/agilerl/__init__.py +0 -34
- agilerl-2.8.0.dev1/agilerl/components/multi_agent_replay_buffer.py +0 -242
- agilerl-2.8.0.dev1/agilerl/training/train_llm.py +0 -1908
- agilerl-2.8.0.dev1/agilerl/training/train_multi_agent_off_policy.py +0 -612
- agilerl-2.8.0.dev1/agilerl/training/train_multi_agent_on_policy.py +0 -623
- agilerl-2.8.0.dev1/agilerl/training/train_off_policy.py +0 -617
- agilerl-2.8.0.dev1/agilerl/training/train_on_policy.py +0 -511
- agilerl-2.8.0.dev1/agilerl/wrappers/__init__.py +0 -0
- agilerl-2.8.0.dev1/benchmarking/benchmarking_bandits.py +0 -146
- agilerl-2.8.0.dev1/benchmarking/benchmarking_llm_multiturn.py +0 -156
- agilerl-2.8.0.dev1/benchmarking/benchmarking_llm_preference.py +0 -176
- agilerl-2.8.0.dev1/benchmarking/benchmarking_llm_reasoning.py +0 -198
- agilerl-2.8.0.dev1/benchmarking/benchmarking_multi_agent_off_policy.py +0 -224
- agilerl-2.8.0.dev1/benchmarking/benchmarking_multi_agent_on_policy.py +0 -169
- agilerl-2.8.0.dev1/benchmarking/benchmarking_off_policy.py +0 -179
- agilerl-2.8.0.dev1/benchmarking/benchmarking_off_policy_distributed.py +0 -107
- agilerl-2.8.0.dev1/benchmarking/benchmarking_offline.py +0 -148
- agilerl-2.8.0.dev1/benchmarking/benchmarking_offline_distributed.py +0 -144
- agilerl-2.8.0.dev1/benchmarking/benchmarking_on_policy.py +0 -118
- agilerl-2.8.0.dev1/benchmarking/benchmarking_rainbow.py +0 -175
- agilerl-2.8.0.dev1/benchmarking/benchmarking_recurrent.py +0 -176
- agilerl-2.8.0.dev1/benchmarking/benchmarking_resnet.py +0 -110
- agilerl-2.8.0.dev1/benchmarking/benchmarking_sft.py +0 -172
- agilerl-2.8.0.dev1/benchmarking/benchmarking_simba.py +0 -131
- agilerl-2.8.0.dev1/benchmarking/configs/ds_config.json +0 -16
- agilerl-2.8.0.dev1/benchmarking/make_evolvable_benchmarking.py +0 -490
- agilerl-2.8.0.dev1/benchmarking/networks.py +0 -569
- agilerl-2.8.0.dev1/configs/accelerate/accelerate.yaml +0 -13
- agilerl-2.8.0.dev1/configs/accelerate/bench_accelerate_config.yaml +0 -25
- agilerl-2.8.0.dev1/configs/accelerate/grpo_accelerate_config.yaml +0 -25
- agilerl-2.8.0.dev1/configs/training/bandit/neural_ts.yaml +0 -53
- agilerl-2.8.0.dev1/configs/training/bandit/neural_ucb.yaml +0 -53
- agilerl-2.8.0.dev1/configs/training/cqn.yaml +0 -55
- agilerl-2.8.0.dev1/configs/training/ddpg/ddpg.yaml +0 -70
- agilerl-2.8.0.dev1/configs/training/ddpg/ddpg_lstm.yaml +0 -69
- agilerl-2.8.0.dev1/configs/training/ddpg/ddpg_simba.yaml +0 -71
- agilerl-2.8.0.dev1/configs/training/dqn/dqn.yaml +0 -56
- agilerl-2.8.0.dev1/configs/training/dqn/dqn_lstm.yaml +0 -64
- agilerl-2.8.0.dev1/configs/training/dqn/dqn_rainbow.yaml +0 -69
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/cispo.yaml +0 -47
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/cispo_quant_bench.yaml +0 -114
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/cispo_quant_bench_qwen.yaml +0 -69
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/dpo.yaml +0 -50
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/grpo.yaml +0 -42
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/grpo_multiturn.yaml +0 -41
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/gspo.yaml +0 -45
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/ppo_llm.yaml +0 -44
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/ppo_llm_quant_bench.yaml +0 -68
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/reinforce_llm.yaml +0 -40
- agilerl-2.8.0.dev1/configs/training/llm_finetuning/reinforce_quant_bench.yaml +0 -80
- agilerl-2.8.0.dev1/configs/training/multi_agent/ippo.yaml +0 -78
- agilerl-2.8.0.dev1/configs/training/multi_agent/ippo_pong.yaml +0 -69
- agilerl-2.8.0.dev1/configs/training/multi_agent/maddpg.yaml +0 -94
- agilerl-2.8.0.dev1/configs/training/multi_agent/matd3.yaml +0 -70
- agilerl-2.8.0.dev1/configs/training/multi_input.yaml +0 -64
- agilerl-2.8.0.dev1/configs/training/ppo/ppo.yaml +0 -73
- agilerl-2.8.0.dev1/configs/training/ppo/ppo_image.yaml +0 -86
- agilerl-2.8.0.dev1/configs/training/ppo/ppo_recurrent.yaml +0 -65
- agilerl-2.8.0.dev1/configs/training/sft.yaml +0 -43
- agilerl-2.8.0.dev1/configs/training/td3.yaml +0 -64
- agilerl-2.8.0.dev1/data/cartpole/cartpole_random_v1.1.0.h5 +0 -0
- agilerl-2.8.0.dev1/data/cartpole/cartpole_v1.1.0.h5 +0 -0
- agilerl-2.8.0.dev1/data/pendulum/pendulum_random_v1.1.0.h5 +0 -0
- agilerl-2.8.0.dev1/data/pendulum/pendulum_v1.1.0.h5 +0 -0
- agilerl-2.8.0.dev1/debugging/__init__.py +0 -0
- agilerl-2.8.0.dev1/demos/bandits/demo_bandit.py +0 -188
- agilerl-2.8.0.dev1/demos/llm/debugging/config_load.py +0 -22
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/grpo_constant_target.yaml +0 -24
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/grpo_grid_navigation.yaml +0 -26
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/ppo_conditional_target.yaml +0 -31
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/ppo_constant_target.yaml +0 -27
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/ppo_grid_navigation.yaml +0 -29
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/ppo_multi_input.yaml +0 -28
- agilerl-2.8.0.dev1/demos/llm/debugging/configs/ppo_value_head.yaml +0 -30
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_llm.py +0 -183
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_llm_stage_1.py +0 -249
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_llm_stage_2.py +0 -280
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_llm_stage_3.py +0 -395
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_llm_training_matrix.py +0 -696
- agilerl-2.8.0.dev1/demos/llm/debugging/debugging_value.py +0 -190
- agilerl-2.8.0.dev1/demos/llm/debugging/llm_debug_utils.py +0 -16
- agilerl-2.8.0.dev1/demos/llm/debugging/tiny_model.py +0 -229
- agilerl-2.8.0.dev1/demos/llm/demo_llm_finetuning.py +0 -342
- agilerl-2.8.0.dev1/demos/multi_agent/demo_multi_agent.py +0 -253
- agilerl-2.8.0.dev1/demos/single_agent/demo_custom_network.py +0 -222
- agilerl-2.8.0.dev1/demos/single_agent/demo_off_policy.py +0 -196
- agilerl-2.8.0.dev1/demos/single_agent/demo_off_policy_distributed.py +0 -226
- agilerl-2.8.0.dev1/demos/single_agent/demo_offline.py +0 -147
- agilerl-2.8.0.dev1/demos/single_agent/demo_offline_distributed.py +0 -188
- agilerl-2.8.0.dev1/demos/single_agent/demo_on_policy.py +0 -155
- agilerl-2.8.0.dev1/demos/single_agent/demo_on_policy_rnn_cartpole.py +0 -276
- agilerl-2.8.0.dev1/demos/single_agent/demo_on_policy_rnn_memory.py +0 -348
- agilerl-2.8.0.dev1/demos/single_agent/demo_on_policy_rnn_minigrid.py +0 -315
- agilerl-2.8.0.dev1/demos/single_agent/performance_flamegraph_cartpole.py +0 -226
- agilerl-2.8.0.dev1/demos/single_agent/performance_flamegraph_lunar_lander.py +0 -230
- agilerl-2.8.0.dev1/demos/single_agent/performance_flamegraph_lunar_lander_rnn.py +0 -240
- agilerl-2.8.0.dev1/demos/single_agent/performance_flamegraph_rnn_memory.py +0 -280
- agilerl-2.8.0.dev1/docker +0 -10159
- agilerl-2.8.0.dev1/docs/Makefile +0 -20
- agilerl-2.8.0.dev1/docs/__init__.py +0 -1
- agilerl-2.8.0.dev1/docs/_static/arena-github-badge.svg +0 -1
- agilerl-2.8.0.dev1/docs/_static/css/custom.css +0 -0
- agilerl-2.8.0.dev1/docs/_static/favicon.ico +0 -0
- agilerl-2.8.0.dev1/docs/_static/js/expand_sidebar.js +0 -6
- agilerl-2.8.0.dev1/docs/_static/logo_teal.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/logo_white.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/module.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/multi_turn_llm_benchmarks.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/network.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/thumbnails/iris-thumbnail.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/thumbnails/pendigits-thumbnail.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/thumbnails/rainbow_performance.png +0 -0
- agilerl-2.8.0.dev1/docs/_static/thumbnails/simba_thumbnail.png +0 -0
- agilerl-2.8.0.dev1/docs/api/algorithms/base.rst +0 -292
- agilerl-2.8.0.dev1/docs/api/algorithms/cispo.rst +0 -137
- agilerl-2.8.0.dev1/docs/api/algorithms/cql.rst +0 -174
- agilerl-2.8.0.dev1/docs/api/algorithms/ddpg.rst +0 -196
- agilerl-2.8.0.dev1/docs/api/algorithms/dpo.rst +0 -121
- agilerl-2.8.0.dev1/docs/api/algorithms/dqn.rst +0 -166
- agilerl-2.8.0.dev1/docs/api/algorithms/dqn_rainbow.rst +0 -175
- agilerl-2.8.0.dev1/docs/api/algorithms/grpo.rst +0 -103
- agilerl-2.8.0.dev1/docs/api/algorithms/gspo.rst +0 -134
- agilerl-2.8.0.dev1/docs/api/algorithms/ilql.rst +0 -15
- agilerl-2.8.0.dev1/docs/api/algorithms/index.rst +0 -187
- agilerl-2.8.0.dev1/docs/api/algorithms/ippo.rst +0 -344
- agilerl-2.8.0.dev1/docs/api/algorithms/llmppo.rst +0 -161
- agilerl-2.8.0.dev1/docs/api/algorithms/llmreinforce.rst +0 -182
- agilerl-2.8.0.dev1/docs/api/algorithms/maddpg.rst +0 -274
- agilerl-2.8.0.dev1/docs/api/algorithms/matd3.rst +0 -273
- agilerl-2.8.0.dev1/docs/api/algorithms/neural_ts.rst +0 -154
- agilerl-2.8.0.dev1/docs/api/algorithms/neural_ucb.rst +0 -155
- agilerl-2.8.0.dev1/docs/api/algorithms/ppo.rst +0 -222
- agilerl-2.8.0.dev1/docs/api/algorithms/registry.rst +0 -19
- agilerl-2.8.0.dev1/docs/api/algorithms/sft.rst +0 -131
- agilerl-2.8.0.dev1/docs/api/algorithms/td3.rst +0 -185
- agilerl-2.8.0.dev1/docs/api/algorithms/wrappers.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/components/data.rst +0 -46
- agilerl-2.8.0.dev1/docs/api/components/index.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/components/multi_agent_replay_buffer.rst +0 -27
- agilerl-2.8.0.dev1/docs/api/components/replay_buffer.rst +0 -35
- agilerl-2.8.0.dev1/docs/api/components/rollout_buffer.rst +0 -61
- agilerl-2.8.0.dev1/docs/api/components/sampler.rst +0 -37
- agilerl-2.8.0.dev1/docs/api/components/segment_tree.rst +0 -37
- agilerl-2.8.0.dev1/docs/api/hpo/index.rst +0 -14
- agilerl-2.8.0.dev1/docs/api/hpo/mutation.rst +0 -45
- agilerl-2.8.0.dev1/docs/api/hpo/tournament.rst +0 -28
- agilerl-2.8.0.dev1/docs/api/modules/base.rst +0 -33
- agilerl-2.8.0.dev1/docs/api/modules/bert.rst +0 -17
- agilerl-2.8.0.dev1/docs/api/modules/cnn.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/modules/custom_activation.rst +0 -7
- agilerl-2.8.0.dev1/docs/api/modules/dummy.rst +0 -14
- agilerl-2.8.0.dev1/docs/api/modules/gpt.rst +0 -26
- agilerl-2.8.0.dev1/docs/api/modules/index.rst +0 -26
- agilerl-2.8.0.dev1/docs/api/modules/lstm.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/modules/mlp.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/modules/multi_input.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/modules/resnet.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/modules/simba.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/networks/actors.rst +0 -28
- agilerl-2.8.0.dev1/docs/api/networks/base.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/networks/index.rst +0 -18
- agilerl-2.8.0.dev1/docs/api/networks/q_networks.rst +0 -28
- agilerl-2.8.0.dev1/docs/api/networks/value_networks.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/rollouts/index.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/rollouts/on_policy.rst +0 -42
- agilerl-2.8.0.dev1/docs/api/train.rst +0 -25
- agilerl-2.8.0.dev1/docs/api/utils/algo_utils.rst +0 -105
- agilerl-2.8.0.dev1/docs/api/utils/cache.rst +0 -7
- agilerl-2.8.0.dev1/docs/api/utils/evolvable_networks.rst +0 -65
- agilerl-2.8.0.dev1/docs/api/utils/ilql_utils.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/utils/index.rst +0 -16
- agilerl-2.8.0.dev1/docs/api/utils/llm_utils.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/utils/log_utils.rst +0 -9
- agilerl-2.8.0.dev1/docs/api/utils/minari_utils.rst +0 -8
- agilerl-2.8.0.dev1/docs/api/utils/probe_envs.rst +0 -386
- agilerl-2.8.0.dev1/docs/api/utils/torch_utils.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/utils/utils.rst +0 -34
- agilerl-2.8.0.dev1/docs/api/vector/index.rst +0 -8
- agilerl-2.8.0.dev1/docs/api/vector/petting_zoo_async_vector_env.rst +0 -62
- agilerl-2.8.0.dev1/docs/api/vector/petting_zoo_vector_env.rst +0 -10
- agilerl-2.8.0.dev1/docs/api/wrappers/agent.rst +0 -28
- agilerl-2.8.0.dev1/docs/api/wrappers/index.rst +0 -11
- agilerl-2.8.0.dev1/docs/api/wrappers/learning.rst +0 -17
- agilerl-2.8.0.dev1/docs/api/wrappers/llm_envs.rst +0 -12
- agilerl-2.8.0.dev1/docs/api/wrappers/make_evolvable.rst +0 -8
- agilerl-2.8.0.dev1/docs/api/wrappers/pettingzoo.rst +0 -8
- agilerl-2.8.0.dev1/docs/bandits/index.rst +0 -336
- agilerl-2.8.0.dev1/docs/conf.py +0 -80
- agilerl-2.8.0.dev1/docs/custom_algorithms/index.rst +0 -75
- agilerl-2.8.0.dev1/docs/debugging_rl/index.rst +0 -368
- agilerl-2.8.0.dev1/docs/distributed_training/index.rst +0 -253
- agilerl-2.8.0.dev1/docs/evo_hyperparam_opt/index.rst +0 -242
- agilerl-2.8.0.dev1/docs/evolvable_networks/index.rst +0 -593
- agilerl-2.8.0.dev1/docs/get_started/agilerl2changes.rst +0 -66
- agilerl-2.8.0.dev1/docs/get_started/index.rst +0 -445
- agilerl-2.8.0.dev1/docs/index.rst +0 -162
- agilerl-2.8.0.dev1/docs/llm_finetuning/fused_logprobs.rst +0 -172
- agilerl-2.8.0.dev1/docs/llm_finetuning/index.rst +0 -81
- agilerl-2.8.0.dev1/docs/llm_finetuning/llm_checkpoints.rst +0 -146
- agilerl-2.8.0.dev1/docs/llm_finetuning/quantization.rst +0 -346
- agilerl-2.8.0.dev1/docs/llm_finetuning/vllm_sleep_handoff.md +0 -74
- agilerl-2.8.0.dev1/docs/make.bat +0 -35
- agilerl-2.8.0.dev1/docs/multi_agent_training/index.rst +0 -700
- agilerl-2.8.0.dev1/docs/off_policy/index.rst +0 -340
- agilerl-2.8.0.dev1/docs/offline_training/index.rst +0 -300
- agilerl-2.8.0.dev1/docs/on_policy/index.rst +0 -503
- agilerl-2.8.0.dev1/docs/pomdp/index.rst +0 -35
- agilerl-2.8.0.dev1/docs/releases/index.rst +0 -7
- agilerl-2.8.0.dev1/docs/requirements.txt +0 -6
- agilerl-2.8.0.dev1/find_dqn_commit.sh +0 -82
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/multiturn:GRPO:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/multiturn:LLMPPO:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/multiturn:LLMReinforce:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/preference:DPO:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/reasoning:GRPO:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/reasoning:LLMPPO:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/saved_checkpoints/debug_matrix/reasoning:LLMReinforce:pop1:no_tournament/attributes.pt +0 -0
- agilerl-2.8.0.dev1/sitecustomize.py +0 -12
- agilerl-2.8.0.dev1/tests/__init__.py +0 -5
- agilerl-2.8.0.dev1/tests/assets/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/assets/build_minari_fixture.py +0 -67
- agilerl-2.8.0.dev1/tests/assets/build_tiny_llm_fixture.py +0 -129
- agilerl-2.8.0.dev1/tests/assets/minari_cache/D4RL/door/human-v2/data/main_data.hdf5 +0 -0
- agilerl-2.8.0.dev1/tests/assets/minari_cache/D4RL/door/human-v2/data/metadata.json +0 -1
- agilerl-2.8.0.dev1/tests/assets/minari_cache/D4RL/door/namespace_metadata.json +0 -1
- agilerl-2.8.0.dev1/tests/assets/minari_cache/D4RL/namespace_metadata.json +0 -1
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/added_tokens.json +0 -24
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/chat_template.jinja +0 -54
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/config.json +0 -32
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/generation_config.json +0 -6
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/model.safetensors +0 -0
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/special_tokens_map.json +0 -31
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/tokenizer.json +0 -1
- agilerl-2.8.0.dev1/tests/assets/tiny_llm/tokenizer_config.json +0 -207
- agilerl-2.8.0.dev1/tests/conftest.py +0 -539
- agilerl-2.8.0.dev1/tests/helper_functions.py +0 -356
- agilerl-2.8.0.dev1/tests/helpers/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/helpers/algorithm_coverage.py +0 -31
- agilerl-2.8.0.dev1/tests/pz_vector_test_utils.py +0 -488
- agilerl-2.8.0.dev1/tests/subprocess_runner.py +0 -240
- agilerl-2.8.0.dev1/tests/test_algorithms/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/conftest.py +0 -39
- agilerl-2.8.0.dev1/tests/test_algorithms/test_bandits/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_bandits/test_neural_ts.py +0 -520
- agilerl-2.8.0.dev1/tests/test_algorithms/test_bandits/test_neural_ucb.py +0 -531
- agilerl-2.8.0.dev1/tests/test_algorithms/test_base.py +0 -1682
- agilerl-2.8.0.dev1/tests/test_algorithms/test_bc_lm.py +0 -1235
- agilerl-2.8.0.dev1/tests/test_algorithms/test_core_base.py +0 -6423
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llm_ops/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llm_ops/test_fused_logprobs.py +0 -104
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llm_ops/test_fused_lora.py +0 -403
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llm_ops/test_fused_loss.py +0 -1291
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/conftest.py +0 -115
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_dpo.py +0 -950
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_grpo.py +0 -6151
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_llm_checkpoint.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_ppo_llm.py +0 -1875
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_quantization.py +0 -969
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_reinforce_llm.py +0 -1469
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_sft.py +0 -935
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_vllm.py +0 -332
- agilerl-2.8.0.dev1/tests/test_algorithms/test_llms/test_vllm_colocate.py +0 -314
- agilerl-2.8.0.dev1/tests/test_algorithms/test_multi_agent/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_multi_agent/conftest.py +0 -42
- agilerl-2.8.0.dev1/tests/test_algorithms/test_multi_agent/test_ippo.py +0 -2199
- agilerl-2.8.0.dev1/tests/test_algorithms/test_multi_agent/test_maddpg.py +0 -1938
- agilerl-2.8.0.dev1/tests/test_algorithms/test_multi_agent/test_matd3.py +0 -2138
- agilerl-2.8.0.dev1/tests/test_algorithms/test_optimizer_wrapper.py +0 -1543
- agilerl-2.8.0.dev1/tests/test_algorithms/test_param_docstrings.py +0 -102
- agilerl-2.8.0.dev1/tests/test_algorithms/test_registry.py +0 -1151
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_cqn.py +0 -590
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_ddpg.py +0 -872
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_dqn.py +0 -649
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_dqn_rainbow.py +0 -857
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_ilql.py +0 -1335
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_ppo.py +0 -2245
- agilerl-2.8.0.dev1/tests/test_algorithms/test_single_agent/test_td3.py +0 -1119
- agilerl-2.8.0.dev1/tests/test_components/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_components/test_multi_agent_replay_buffer.py +0 -638
- agilerl-2.8.0.dev1/tests/test_components/test_replay_buffer.py +0 -1056
- agilerl-2.8.0.dev1/tests/test_components/test_replay_data.py +0 -170
- agilerl-2.8.0.dev1/tests/test_components/test_rollout_buffer.py +0 -2129
- agilerl-2.8.0.dev1/tests/test_components/test_sampler.py +0 -485
- agilerl-2.8.0.dev1/tests/test_components/test_segment_tree.py +0 -129
- agilerl-2.8.0.dev1/tests/test_data.py +0 -456
- agilerl-2.8.0.dev1/tests/test_hpo/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_hpo/test_mutation.py +0 -2284
- agilerl-2.8.0.dev1/tests/test_hpo/test_reinit_shared_networks.py +0 -56
- agilerl-2.8.0.dev1/tests/test_hpo/test_tournament.py +0 -522
- agilerl-2.8.0.dev1/tests/test_init.py +0 -25
- agilerl-2.8.0.dev1/tests/test_modules/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_modules/test_base.py +0 -978
- agilerl-2.8.0.dev1/tests/test_modules/test_bert.py +0 -456
- agilerl-2.8.0.dev1/tests/test_modules/test_cnn.py +0 -1064
- agilerl-2.8.0.dev1/tests/test_modules/test_cnn_cpu.py +0 -112
- agilerl-2.8.0.dev1/tests/test_modules/test_configs.py +0 -92
- agilerl-2.8.0.dev1/tests/test_modules/test_custom_activation.py +0 -27
- agilerl-2.8.0.dev1/tests/test_modules/test_dummy.py +0 -86
- agilerl-2.8.0.dev1/tests/test_modules/test_gpt.py +0 -455
- agilerl-2.8.0.dev1/tests/test_modules/test_lstm.py +0 -494
- agilerl-2.8.0.dev1/tests/test_modules/test_mlp.py +0 -291
- agilerl-2.8.0.dev1/tests/test_modules/test_multi_input.py +0 -1103
- agilerl-2.8.0.dev1/tests/test_modules/test_multi_input_cpu.py +0 -77
- agilerl-2.8.0.dev1/tests/test_modules/test_resnet.py +0 -443
- agilerl-2.8.0.dev1/tests/test_modules/test_simba.py +0 -357
- agilerl-2.8.0.dev1/tests/test_networks/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_networks/test_actors.py +0 -855
- agilerl-2.8.0.dev1/tests/test_networks/test_base.py +0 -550
- agilerl-2.8.0.dev1/tests/test_networks/test_distributions.py +0 -280
- agilerl-2.8.0.dev1/tests/test_networks/test_q_networks.py +0 -655
- agilerl-2.8.0.dev1/tests/test_networks/test_value_functions.py +0 -190
- agilerl-2.8.0.dev1/tests/test_protocols.py +0 -586
- agilerl-2.8.0.dev1/tests/test_rollouts/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_rollouts/test_on_policy.py +0 -396
- agilerl-2.8.0.dev1/tests/test_train/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_train/test_train.py +0 -5510
- agilerl-2.8.0.dev1/tests/test_train/test_train_llm.py +0 -2910
- agilerl-2.8.0.dev1/tests/test_utils/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_utils/test_algo_utils.py +0 -2020
- agilerl-2.8.0.dev1/tests/test_utils/test_cache.py +0 -62
- agilerl-2.8.0.dev1/tests/test_utils/test_ilql_utils.py +0 -82
- agilerl-2.8.0.dev1/tests/test_utils/test_llm_packing.py +0 -375
- agilerl-2.8.0.dev1/tests/test_utils/test_llm_utils.py +0 -2794
- agilerl-2.8.0.dev1/tests/test_utils/test_log_utils.py +0 -230
- agilerl-2.8.0.dev1/tests/test_utils/test_minari_utils.py +0 -317
- agilerl-2.8.0.dev1/tests/test_utils/test_ppo_value_head.py +0 -481
- agilerl-2.8.0.dev1/tests/test_utils/test_probe_envs.py +0 -814
- agilerl-2.8.0.dev1/tests/test_utils/test_probe_envs_llm.py +0 -268
- agilerl-2.8.0.dev1/tests/test_utils/test_probe_envs_ma.py +0 -855
- agilerl-2.8.0.dev1/tests/test_utils/test_sampling_utils.py +0 -175
- agilerl-2.8.0.dev1/tests/test_utils/test_torch_utils.py +0 -320
- agilerl-2.8.0.dev1/tests/test_utils/test_utils.py +0 -1716
- agilerl-2.8.0.dev1/tests/test_utils/test_utils_evolvable.py +0 -804
- agilerl-2.8.0.dev1/tests/test_vector/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_vector/test_vector.py +0 -1821
- agilerl-2.8.0.dev1/tests/test_wrappers/__init__.py +0 -0
- agilerl-2.8.0.dev1/tests/test_wrappers/test_agent.py +0 -2045
- agilerl-2.8.0.dev1/tests/test_wrappers/test_autoreset.py +0 -282
- agilerl-2.8.0.dev1/tests/test_wrappers/test_bandit_env.py +0 -52
- agilerl-2.8.0.dev1/tests/test_wrappers/test_llm_envs.py +0 -1192
- agilerl-2.8.0.dev1/tests/test_wrappers/test_make_evolvable.py +0 -1350
- agilerl-2.8.0.dev1/tests/test_wrappers/test_multiturn_wrappers.py +0 -1284
- agilerl-2.8.0.dev1/tests/test_wrappers/test_skills.py +0 -62
- agilerl-2.8.0.dev1/tests/utils.py +0 -373
- agilerl-2.8.0.dev1/uv.lock +0 -7411
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/LICENSE +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/bc_lm.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/cispo.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/llm_ops/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/llm_ops/fused_logprobs.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/llm_ops/fused_lora.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/llm_ops/fused_loss.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/llm_ops/vllm_colocate.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/core/optimizer_wrapper.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/algorithms/gspo.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/data/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/data/language_environment.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/data/rl_data.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/data/tokenizer.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/data/torch_datasets.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/hpo/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/base.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/search.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/sync_vec_env.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/llm_envs/token_observation.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/base.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/bert.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/cnn.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/configs.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/custom_components.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/dummy.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/gpt.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/lstm.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/mlp.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/multi_input.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/resnet.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/modules/simba.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/custom_modules.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/networks/distributions.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/rollouts/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/training/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/cache.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/ilql_utils.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/llm_packing.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/log_utils.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/ppo_value_head.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/probe_envs_llm.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/sampling_utils.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/utils/torch_utils.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/vector/pz_async_vec_env.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/vector/pz_vec_env.py +0 -0
- {agilerl-2.8.0.dev1/agilerl/vector → agilerl-2.8.0.dev2/agilerl/wrappers}/__init__.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/llm_envs.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/make_evolvable.py +0 -0
- {agilerl-2.8.0.dev1 → agilerl-2.8.0.dev2}/agilerl/wrappers/utils.py +0 -0
|
@@ -1,3 +1,6 @@
|
|
|
1
|
+
# Symlink for Pylance/Pyright type checking of namespace package (repo root only)
|
|
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
|
+
# Symlink for type-checking (repo root only)
|
|
166
|
+
/agilerl/arena/
|