提交历史

作者 SHA1 备注 提交日期
  gjoliver 9226f9bddc [RLlib] Report timesteps_this_iter to Tune, so it can track/checkpoint/restore total timesteps trained. (#19264) 3 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 c3a15ecc0f [RLlib] Issue #13802: Enhance metrics for `multiagent->count_steps_by=agent_steps` setting. (#14033) 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 b0b0463161 [RLlib] Trajectory View API (preparatory cleanup and enhancements). (#9678) 4 年之前
  Eric Liang 1e0e1a45e6 [rllib] Add type annotations for evaluation/, env/ packages (#9003) 4 年之前
  Eric Liang 9f04a65922 [rllib] Add PPO+DQN two trainer multiagent workflow example (#8334) 4 年之前
  Eric Liang baadbdf8d4 [rllib] Execute PPO using training workflow (#8206) 4 年之前
  Eric Liang 31b40b00f6 [rllib] Pull out experimental dsl into rllib.execution module, add initial unit tests (#7958) 4 年之前