Commit History

Author SHA1 Message Date
  Sven Mika 60b2219d72 [RLlib] Allow for evaluation to run by `timesteps` (alternative to `episodes`) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757) 2 years ago
  Avnish Narayan 026bf01071 [RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) 3 years ago
  Sven Mika 839fc59224 [RLlib] CQL TensorFlow support (#15841) 3 years ago
  Sven Mika c4a3e1589b [RLlib] CQL: Bug fixes and OPE example added to test and offline_rl.py example. (#15761) 3 years ago
  Michael Luo 4cbe13cdfd [RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. (#15603) 3 years ago