提交历史

作者 SHA1 备注 提交日期
  Eric Liang 3febc5e107 [data] Revert the dataset to datastream class rename (#35082) 1 年之前
  Jiajun Yao e73eba20af [docs] Fix broken links (#34665) 1 年之前
  Eric Liang c0dff99a03 [data] [docs] Datastream docs rename [5/n] (#34512) 1 年之前
  Sven Mika d429363a47 [RLlib] [RELEASE BLOCKER] Fix RLlib CLI: e.g. `rllib example run cartpole-ppo` fails. (#30664) 1 年之前
  Sven Mika 9ece8acb0c [RLlib] Docs update: New Algorithm checkpoints, Policy checkpoints and Policy model exports in native format (#28812) 2 年之前
  kourosh hakhamaneshi 5779ee764d [RLlib] Fix ope v_gain (#28136) 2 年之前
  Rohan Potdar 600b8d4729 [RLlib]: Fix OPE docs. (#27460) 2 年之前
  Rohan Potdar deccf33912 [RLlib]: Add Off-Policy Estimation docs (#26809) 2 年之前
  Rohan Potdar 09ce4711fd [RLlib]: Move OPE to evaluation config (#25911) 2 年之前
  Sven Mika 130b7eeaba [RLlib] `Trainer` to `Algorithm` renaming. (#25539) 2 年之前
  Rohan Potdar a9d8da0100 [RLlib]: Doubly Robust Off-Policy Evaluation. (#25056) 2 年之前
  Sven Mika a559efb7e4 [CI; LinkCheck] 3 RLlib fixes. (#25476) 2 年之前
  Sven Mika b5bc2b93c3 [RLlib] Move all remaining algos into `algorithms` directory. (#25366) 2 年之前
  Yi Cheng fd0f967d2e Revert "[RLlib] Move (A/DD)?PPO and IMPALA algos to `algorithms` dir and rename policy and trainer classes. (#25346)" (#25420) 2 年之前
  Sven Mika e4ceae19ef [RLlib] Move (A/DD)?PPO and IMPALA algos to `algorithms` dir and rename policy and trainer classes. (#25346) 2 年之前
  Rohan Potdar ab81c8e9ca [RLlib]: Rename `input_evaluation` to `off_policy_estimation_methods`. (#25107) 2 年之前
  Steven Morad 501d932449 [RLlib] SAC, RNNSAC, and CQL TrainerConfig objects (#25059) 2 年之前
  Christy Bergman 76eb47e226 [RLlib; docs] Rename UCB -> LinUCB. (#24348) 2 年之前
  Sven Mika 5b61a00792 [RLlib] Feed all values in COMMON_CONFIG directly from TrainerConfig() (removes duplicate values and comments). (#24433) 2 年之前
  Jeroen Bédorf 1263015931 [RLlib] Add support for writing env 'info' dicts to output datasets for TFPolicies (for TorchPolicies, these are part of the view-requirements by default and thus written either way). (#24041) 2 年之前
  Max Pumperla 11c40e363d [docs] external promo content (#22823) 2 年之前
  Max Pumperla 9482f03134 [docs] RLlib concepts consolidation, user guide, RL conf prep (#22496) 2 年之前
  Jun Gong 6f5afcbce9 [RLlib] Docs enhancements: Setup-dev instructions; Ray datasets integration. (#22239) 2 年之前
  Max Pumperla f9b71a8bf6 [docs] new structure (#21776) 2 年之前