提交历史

作者 SHA1 备注 提交日期
  Sven Mika 5a3954eff7 [RLlib] APPO+new-stack (Atari benchmark) - Preparatory PR 01. (#34743) 1 年之前
  kourosh hakhamaneshi 8d2dc9a399 [RLlib] Change default framework from tf to torch (#33604) 1 年之前
  Sven Mika 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) 1 年之前
  Artur Niederfahrenhorst 0dceddb912 [RLlib] Move learning_starts logic from buffers into `training_step()`. (#26032) 2 年之前
  Sven Mika 7c39aa5fac [RLlib] Trainer.training_iteration -> Trainer.training_step; Iterations vs reportings: Clarification of terms. (#25076) 2 年之前
  Artur Niederfahrenhorst fb2915d26a [RLlib] Replay Buffer API and Ape-X. (#24506) 2 年之前
  Sven Mika f066180ed5 [RLlib] Deprecate `timesteps_per_iteration` config key (in favor of `min_[sample|train]_timesteps_per_reporting`. (#24372) 2 年之前
  Artur Niederfahrenhorst 9a64bd4e9b [RLlib] Simple-Q uses training iteration fn (instead of execution_plan); ReplayBuffer API for Simple-Q (#22842) 2 年之前
  Sven Mika 2746fc0476 [RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520) 4 年之前
  Sven Mika baa053496a [RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414) 4 年之前