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.
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.coveragerc +1 -0
- agilerl-2.5.0.dev0/.github/workflows/python-app.yml +56 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.gitignore +1 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.pre-commit-config.yaml +8 -16
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/PKG-INFO +7 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/README.md +1 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/bc_lm.py +158 -100
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/base.py +514 -393
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/optimizer_wrapper.py +88 -86
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/registry.py +68 -68
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/cqn.py +30 -25
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ddpg.py +130 -94
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dpo.py +21 -20
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dqn.py +40 -31
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/dqn_rainbow.py +81 -45
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/grpo.py +49 -31
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ilql.py +461 -294
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ippo.py +155 -109
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/maddpg.py +122 -98
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/matd3.py +150 -118
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/neural_ts_bandit.py +37 -28
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/neural_ucb_bandit.py +38 -29
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/ppo.py +222 -163
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/td3.py +164 -105
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/data.py +19 -17
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/multi_agent_replay_buffer.py +33 -36
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/replay_buffer.py +37 -37
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/rollout_buffer.py +165 -114
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/sampler.py +43 -25
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/segment_tree.py +26 -22
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/language_environment.py +12 -6
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/rl_data.py +75 -23
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/tokenizer.py +13 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/torch_datasets.py +12 -12
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/mutation.py +195 -123
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/tournament.py +16 -18
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/base.py +129 -102
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/bert.py +131 -112
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/cnn.py +95 -77
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/configs.py +45 -41
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/custom_components.py +29 -22
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/dummy.py +7 -5
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/gpt.py +172 -143
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/lstm.py +52 -41
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/mlp.py +43 -34
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/multi_input.py +65 -66
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/resnet.py +24 -19
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/simba.py +25 -18
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/actors.py +116 -90
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/base.py +102 -80
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/custom_modules.py +7 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/distributions.py +49 -33
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/distributions_experimental.py +62 -62
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/q_networks.py +75 -76
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/value_networks.py +16 -16
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/protocols.py +126 -87
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/rollouts/on_policy.py +42 -33
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_bandits.py +47 -39
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_llm.py +116 -107
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_multi_agent_off_policy.py +69 -50
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_multi_agent_on_policy.py +70 -53
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_off_policy.py +103 -67
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_offline.py +49 -46
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/train_on_policy.py +49 -41
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/typing.py +53 -50
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/algo_utils.py +341 -271
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/cache.py +18 -18
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/evolvable_networks.py +130 -80
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/ilql_utils.py +12 -12
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/llm_utils.py +74 -61
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/log_utils.py +16 -16
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/minari_utils.py +21 -21
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/probe_envs.py +382 -150
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/probe_envs_ma.py +365 -162
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/sampling_utils.py +55 -17
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/torch_utils.py +28 -20
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/utils.py +113 -86
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/pz_async_vec_env.py +138 -107
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/pz_vec_env.py +30 -36
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/agent.py +70 -52
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/learning.py +22 -7
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/make_evolvable.py +317 -247
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/pettingzoo_wrappers.py +16 -9
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/utils.py +13 -6
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_bandits.py +12 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_dpo.py +2 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_grpo.py +9 -7
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_multi_agent_off_policy.py +14 -6
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_multi_agent_on_policy.py +5 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_off_policy.py +22 -14
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_off_policy_distributed.py +3 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_offline.py +4 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_offline_distributed.py +1 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_rainbow.py +3 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_recurrent.py +3 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_simba.py +7 -5
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/make_evolvable_benchmarking.py +28 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/networks.py +73 -42
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg.yaml +4 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_bandit.py +16 -10
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_custom_network.py +10 -9
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_multi_agent.py +10 -7
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_off_policy.py +9 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_off_policy_distributed.py +9 -9
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_offline.py +4 -4
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_offline_distributed.py +9 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy.py +8 -6
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_cartpole.py +20 -11
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_memory.py +25 -15
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/demo_on_policy_rnn_minigrid.py +28 -20
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_cartpole.py +14 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_lunar_lander.py +14 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_lunar_lander_rnn.py +14 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/demos/performance_flamegraph_rnn_memory.py +18 -11
- agilerl-2.5.0.dev0/docs/__init__.py +1 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/base.rst +14 -14
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ddpg.rst +29 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/maddpg.rst +8 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/matd3.rst +8 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/td3.rst +29 -4
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/conf.py +3 -3
- agilerl-2.5.0.dev0/pyproject.toml +139 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/conftest.py +27 -19
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/helper_functions.py +78 -74
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/pz_vector_test_utils.py +28 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/test_neural_ts.py +32 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/test_neural_ucb.py +32 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_base.py +385 -44
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bc_lm.py +91 -23
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/conftest.py +1 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/test_dpo.py +13 -9
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/test_grpo.py +184 -95
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_ippo.py +123 -53
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_maddpg.py +196 -68
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/test_matd3.py +211 -74
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_optimizer_wrapper.py +200 -85
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_registry.py +32 -21
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_cqn.py +42 -20
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ddpg.py +124 -72
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_dqn.py +41 -14
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_dqn_rainbow.py +79 -27
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ilql.py +42 -18
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_ppo.py +149 -62
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/test_td3.py +233 -96
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_multi_agent_replay_buffer.py +13 -5
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_replay_buffer.py +1 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_rollout_buffer.py +60 -26
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_data.py +11 -13
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/test_mutation.py +196 -70
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/test_tournament.py +12 -9
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_base.py +58 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_bert.py +29 -7
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_cnn.py +64 -16
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_dummy.py +4 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_gpt.py +14 -4
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_lstm.py +23 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_make_evolvable.py +179 -64
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_mlp.py +24 -10
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_multi_input.py +32 -33
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_simba.py +40 -8
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_actors.py +130 -101
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_base.py +59 -4
- agilerl-2.5.0.dev0/tests/test_networks/test_distributions.py +209 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_q_networks.py +118 -25
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/test_value_functions.py +12 -5
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_protocols.py +67 -18
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_train/test_train.py +392 -217
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_train/test_train_llm.py +16 -21
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_algo_utils.py +123 -23
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_cache.py +2 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_ilql_utils.py +3 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_llm_utils.py +71 -29
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_minari_utils.py +6 -5
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_probe_envs.py +108 -46
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_probe_envs_ma.py +77 -16
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_sampling_utils.py +14 -14
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_torch_utils.py +1 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_utils.py +40 -20
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_utils_evolvable.py +50 -25
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_vector/test_vector.py +161 -106
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_agent.py +84 -45
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_autoreset.py +22 -25
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/uv.lock +1192 -184
- agilerl-2.4.3.dev0/.github/workflows/python-app.yml +0 -59
- agilerl-2.4.3.dev0/pyproject.toml +0 -92
- agilerl-2.4.3.dev0/pytest.ini +0 -31
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/PULL_REQUEST_TEMPLATE/pull_request_template.md +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/badges/arena-github-badge.svg +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.github/workflows/codeql.yml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/.readthedocs.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CITATION.cff +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CODE_OF_CONDUCT.md +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/CONTRIBUTING.md +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/LICENSE +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/__init__.py +7 -7
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/algorithms/core/__init__.py +2 -2
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/components/__init__.py +1 -1
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/data/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/hpo/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/modules/__init__.py +10 -10
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/networks/__init__.py +3 -3
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/rollouts/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/training/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/utils/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/vector/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/agilerl/wrappers/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_on_policy.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/benchmarking_resnet.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/benchmarking/configs/ds_config.json +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/accelerate/accelerate.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/accelerate/grpo_accelerate_config.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/bandit/neural_ts.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/bandit/neural_ucb.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/cqn.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg_lstm.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ddpg/ddpg_simba.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dpo.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn_lstm.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/dqn/dqn_rainbow.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/grpo.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/ippo.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/ippo_pong.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/maddpg.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_agent/matd3.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/multi_input.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo_image.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/ppo/ppo_recurrent.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/configs/training/td3.yaml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/cartpole/cartpole_random_v1.1.0.h5 +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/cartpole/cartpole_v1.1.0.h5 +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/pendulum/pendulum_random_v1.1.0.h5 +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/data/pendulum/pendulum_v1.1.0.h5 +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/dependabot.yml +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/Makefile +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/arena-github-badge.svg +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/css/custom.css +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/favicon.ico +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/js/expand_sidebar.js +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/logo_teal.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/logo_white.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/module.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/network.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/iris-thumbnail.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/pendigits-thumbnail.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/rainbow_performance.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/_static/thumbnails/simba_thumbnail.png +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/cql.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dpo.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dqn.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/dqn_rainbow.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/grpo.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ilql.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ippo.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/neural_ts.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/neural_ucb.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/ppo.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/registry.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/algorithms/wrappers.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/data.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/multi_agent_replay_buffer.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/replay_buffer.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/rollout_buffer.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/sampler.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/components/segment_tree.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/mutation.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/hpo/tournament.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/base.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/bert.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/cnn.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/custom_activation.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/dummy.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/gpt.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/lstm.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/mlp.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/multi_input.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/resnet.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/modules/simba.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/actors.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/base.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/q_networks.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/networks/value_networks.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/rollouts/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/rollouts/on_policy.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/train.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/algo_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/cache.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/evolvable_networks.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/ilql_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/llm_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/log_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/minari_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/probe_envs.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/torch_utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/utils/utils.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/petting_zoo_async_vector_env.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/vector/petting_zoo_vector_env.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/agent.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/learning.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/make_evolvable.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/api/wrappers/pettingzoo.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/bandits/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/custom_algorithms/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/debugging_rl/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/distributed_training/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/evo_hyperparam_opt/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/evolvable_networks/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/get_started/agilerl2changes.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/get_started/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/llm_finetuning/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/make.bat +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/multi_agent_training/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/off_policy/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/offline_training/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/on_policy/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/pomdp/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/releases/index.rst +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/docs/requirements.txt +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_bandits/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_llms/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_multi_agent/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_algorithms/test_single_agent/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_replay_data.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_sampler.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_components/test_segment_tree.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_hpo/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_custom_activation.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_modules/test_resnet.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_networks/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_utils/test_log_utils.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/__init__.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_bandit_env.py +0 -0
- {agilerl-2.4.3.dev0 → agilerl-2.5.0.dev0}/tests/test_wrappers/test_skills.py +0 -0
|
@@ -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 }}
|
|
@@ -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.
|
|
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:
|
|
49
|
-
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
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
|
|
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
|
|
35
|
-
Requires-Dist:
|
|
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
|
[](https://opensource.org/licenses/Apache-2.0)
|
|
59
57
|
[](https://docs.agilerl.com/en/latest/?badge=latest)
|
|
58
|
+
[](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml)
|
|
60
59
|
[](https://pypi.python.org/pypi/agilerl/)
|
|
61
60
|
[](https://discord.gg/eB8HyTA2ux)
|
|
62
61
|
[](https://arena.agilerl.com)
|
|
@@ -7,6 +7,7 @@
|
|
|
7
7
|
|
|
8
8
|
[](https://opensource.org/licenses/Apache-2.0)
|
|
9
9
|
[](https://docs.agilerl.com/en/latest/?badge=latest)
|
|
10
|
+
[](https://github.com/AgileRL/AgileRL/actions/workflows/python-app.yml)
|
|
10
11
|
[](https://pypi.python.org/pypi/agilerl/)
|
|
11
12
|
[](https://discord.gg/eB8HyTA2ux)
|
|
12
13
|
[](https://arena.agilerl.com)
|