Commit History

Author SHA1 Message Date
  Sven Mika 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) 1 year ago
  Sven Mika 72fefc3a40 [RLlib] AlgorithmConfig: Replace more of the old-style config dicts across codebase. (#29799) 2 years ago
  Sven Mika 7c39aa5fac [RLlib] Trainer.training_iteration -> Trainer.training_step; Iterations vs reportings: Clarification of terms. (#25076) 2 years ago
  Sven Mika b5bc2b93c3 [RLlib] Move all remaining algos into `algorithms` directory. (#25366) 2 years ago
  kourosh hakhamaneshi 3815e52a61 [RLlib] Agents to algos: DQN w/o Apex and R2D2, DDPG/TD3, SAC, SlateQ, QMIX, PG, Bandits (#24896) 2 years ago
  Sven Mika f066180ed5 [RLlib] Deprecate `timesteps_per_iteration` config key (in favor of `min_[sample|train]_timesteps_per_reporting`. (#24372) 2 years ago
  Balaji Veeramani 7f1bacc7dc [CI] Format Python code with Black (#21975) 2 years ago
  Sven Mika d5bfb7b7da [RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 (#21652) 2 years ago
  Sven Mika 2746fc0476 [RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520) 4 years ago
  Eric Liang 2298f6fb40 [rllib] Port DQN/Ape-X to training workflow api (#8077) 4 years ago
  Sven Mika 20ef4a8603 [RLlib] Cleanup/unify all test cases. (#7533) 4 years ago
  Sven 60d4d5e1aa Remove future imports (#6724) 4 years ago
  Eric Liang 5d7afe8092 [rllib] Try moving RLlib to top level dir (#5324) 5 years ago