提交历史

作者 SHA1 备注 提交日期
  Sven Mika ea2bea7e30 [RLlib; Docs overhaul] Docstring cleanup: Offline. (#19808) 3 年之前
  Sven Mika 1fd0eb805e [RLlib] Redo fix bug normalize vs unsquash actions (original PR made log-likelihood test flakey). (#17014) 3 年之前
  Amog Kamsetty bc33dc7e96 Revert "[RLlib] Fix bug in policy.py: normalize_actions=True has to call `unsquash_action`, not `normalize_action`." (#17002) 3 年之前
  Sven Mika 7862dd64ea [RLlib] Fix bug in policy.py: normalize_actions=True has to call `unsquash_action`, not `normalize_action`. (#16774) 3 年之前
  Sven Mika 8b3554e37e [RLlib] Remove all (already soft-deprecated) `SampleBatch.data` from code. (#15335) 3 年之前
  Sven Mika f6b84cb2f7 [RLlib] Fix offline logp vs prob bug in OffPolicyEstimator class. (#12158) 3 年之前
  Sven Mika 805dad3bc4 [RLlib] SAC algo cleanup. (#10825) 4 年之前
  Julius Frost dc659ae89a make action probabilities a numpy array (#10122) 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
  Michael Luo b51ab2af66 [RLlib] Offline Type Annotations (#9676) 4 年之前
  Sven Mika 83e06cd30a [RLlib] DDPG refactor and Exploration API action noise classes. (#7314) 4 年之前
  Sven Mika 0db2046b0a [RLlib] Policy.compute_log_likelihoods() and SAC refactor. (issue #7107) (#7124) 4 年之前
  Sven Mika d537e9f0d8 [RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155) 4 年之前
  Sven Mika 6e1c3ea824 [RLlib] Exploration API (+EpsilonGreedy sub-class). (#6974) 4 年之前
  Sven 60d4d5e1aa Remove future imports (#6724) 4 年之前
  Robert Nishihara 39a3459886 Remove (object) from class declarations. (#6658) 4 年之前
  Eric Liang 5d7afe8092 [rllib] Try moving RLlib to top level dir (#5324) 5 年之前