提交历史

作者 SHA1 备注 提交日期
  Vince Jankovics 7dc3de4eed [RLlib] Fix config mismatch for train_one_step. num_sgd_iter instead of sgd_num_iter. (#21555) 2 年之前
  Sven Mika 92f030331e [RLlib] Initial code/comment cleanups in preparation for decentralized multi-agent learner. (#21420) 2 年之前
  Sven Mika 853d10871c [RLlib] Issue 18499: PGTrainer with training_iteration fn does not support multi-GPU. (#21376) 2 年之前
  Sven Mika 62dbf26394 [RLlib] POC: Run PGTrainer w/o the distr. exec API (Trainer's new training_iteration method). (#20984) 2 年之前
  gjoliver e7f9e8ceec [RLlib] Report total_train_steps correctly for offline agents like CQL. (#20541) 2 年之前
  Sven Mika ed85f59194 [RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879) 3 年之前
  Sven Mika 924f11cd45 [RLlib] Torch algos use now-framework-agnostic MultiGPUTrainOneStep execution op (~33% speedup for PPO-torch + GPU). (#17371) 3 年之前
  Sven Mika 5a313ba3d6 [RLlib] Refactor: All tf static graph code should reside inside Policy class. (#17169) 3 年之前
  Sven Mika 18d173b172 [RLlib] Implement policy_maps (multi-agent case) in RolloutWorkers as LRU caches. (#17031) 3 年之前
  Sven Mika 55a90e670a [RLlib] Trainer.add_policy() not working for tf, if added policy is trained afterwards. (#16927) 3 年之前
  Sven Mika 7eb1a29426 [RLlib] Fix ModelV2 custom metrics for torch. (#16734) 3 年之前
  Sven Mika be6db06485 [RLlib] Re-do: Trainer: Support add and delete Policies. (#16569) 3 年之前
  Amog Kamsetty bd3cbfc56a Revert "[RLlib] Allow policies to be added/deleted on the fly. (#16359)" (#16543) 3 年之前
  Sven Mika e78ec370a9 [RLlib] Allow policies to be added/deleted on the fly. (#16359) 3 年之前
  Sven Mika 2303851c3c [RLlib] Torch multi-GPU + LSTM/RNN bug fix. (#15492) 3 年之前
  Sven Mika cecfc3b43b [RLlib] Multi-GPU support for Torch algorithms. (#14709) 3 年之前
  Sven Mika c3a15ecc0f [RLlib] Issue #13802: Enhance metrics for `multiagent->count_steps_by=agent_steps` setting. (#14033) 3 年之前
  Sven Mika 732197e23a [RLlib] Multi-GPU for tf-DQN/PG/A2C. (#13393) 3 年之前
  Sven Mika 775e685531 [RLlib] Issue #13824: `compress_observations=True` crashes for all algos not using a replay buffer. (#14034) 3 年之前
  Sven Mika eb0038612f [RLlib] Extend on_learn_on_batch callback to allow for custom metrics to be added. (#13584) 3 年之前
  Michael Luo a2d1215200 [RLlib] Execution Annotation (#13036) 3 年之前
  Edward Oakes cde711aaf1 Revert "[RLLib] Execution-Folder Type Annotations (#12760)" (#12886) 3 年之前
  Michael Luo becca1424d [RLLib] Execution-Folder Type Annotations (#12760) 3 年之前
  Sven Mika 62c7ab5182 [RLlib] Trajectory view API: Enable by default for PPO, IMPALA, PG, A3C (tf and torch). (#11747) 4 年之前
  Sven Mika 805dad3bc4 [RLlib] SAC algo cleanup. (#10825) 4 年之前
  Sven Mika 2256047876 [RLlib] Rename rllib.utils.types into typing to match built-in python module's name. (#10114) 4 年之前
  Barak Michener 8e76796fd0 ci: Redo `format.sh --all` script & backfill lint fixes (#9956) 4 年之前
  Sven Mika fcdf410ae1 [RLlib] Tf2.x native. (#8752) 4 年之前
  Sven Mika 43043ee4d5 [RLlib] Tf2x preparation; part 2 (upgrading `try_import_tf()`). (#9136) 4 年之前
  Eric Liang 1e0e1a45e6 [rllib] Add type annotations for evaluation/, env/ packages (#9003) 4 年之前