提交历史

作者 SHA1 备注 提交日期
  Sven Mika 698b4eeed3 [RLlib] POC: Separate losses for APPO/IMPALA. Enable TFPolicy to handle multiple optimizers/losses (like TorchPolicy). (#18669) 3 年之前
  Sven Mika 649580d735 [RLlib] Redo simplify multi agent config dict: Reverted b/c seemed to break test_typing (non RLlib test). (#17046) 3 年之前
  Amog Kamsetty 38b5b6d24c Revert "[RLlib] Simplify multiagent config (automatically infer class/spaces/config). (#16565)" (#17036) 3 年之前
  Sven Mika e4123fff27 [RLlib] Simplify multiagent config (automatically infer class/spaces/config). (#16565) 3 年之前
  Kai Fricke 10fd7111b3 [rllib] Improve test learning check, fix flaky two step qmix (#16843) 3 年之前
  Sven Mika 53206dd440 [RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531) 3 年之前
  Sven Mika be6db06485 [RLlib] Re-do: Trainer: Support add and delete Policies. (#16569) 3 年之前
  Sven Mika 169ddabae7 [RLlib] Issue 15973: Trainer.with_updates(validate_config=...) behaves confusingly. (#16429) 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 d2c755ccef [RLlib] Examples scripts add argparse help and replace `--torch` with `--framework`. (#15832) 3 年之前
  Sven Mika c17169dc11 [RLlib] Fix all example scripts to run on GPUs. (#11105) 4 年之前
  Sven Mika 78dfed2683 [RLlib] Issue 8384: QMIX doesn't learn anything. (#9527) 4 年之前