Commit History

Author SHA1 Message Date
  Kai Fricke 246787cdd9 Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284) 2 years ago
  Sven Mika 6f85af435f [RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055) 2 years ago
  gjoliver d8a61f801f [RLlib] Create a set of performance benchmark tests to run nightly. (#19945) 2 years ago
  Sven Mika a931076f59 [RLlib] Tf2 + eager-tracing same speed as framework=tf; Add more test coverage for tf2+tracing. (#19981) 3 years ago
  Sven Mika 2d24ef0d32 [RLlib] Add all simple learning tests as `framework=tf2`. (#19273) 3 years ago
  Sven Mika 0b308719f8 [RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829) 3 years ago
  Carlo Grisetti 5cee8a1985 [release tests] Switch from yaml.load to yaml.safe_load (#19365) 3 years ago
  Sven Mika d439fd7f17 [RLlib] TF2/eager memory leak fixes. (#19198) 3 years ago
  Sven Mika c3e3fc7637 [RLlib] Issue 18280: A3C/IMPALA multi-agent not working. (#19100) 3 years ago
  Sven Mika 73f5c4039b [RLlib] Fix flakey test_a3c, test_maml, test_apex_dqn. (#19035) 3 years ago
  Sven Mika 16ad46a654 [RLlib] Fix broken test_r2d2.py. (#19017) 3 years ago
  Sven Mika ed85f59194 [RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879) 3 years ago
  Sven Mika 828f5d26b7 [RLlib] Custom view requirements (e.g. for prev-n-obs) work with `compute_single_action` and `compute_actions_from_input_dict`. (#18921) 3 years ago
  Sven Mika e6aae61487 [RLlib; testing] Fix bug in stress tests not handling >1 trials per experiment (due to grid-search in IMPALA stress tests). (#18705) 3 years ago
  Sven Mika ba1c489b79 [RLlib Testing] Lower `--smoke-test` "time_total_s" to make sure it doesn't time out. (#18670) 3 years ago
  Sven Mika 8a72824c63 [RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). (#18591) 3 years ago
  Sven Mika 45f60e51a9 [RLlib] DDPPO fixes and benchmarks. (#18390) 3 years ago
  Sven Mika cabaa3b3c6 [RLlib Testing] Add A3C/APPO/BC/DDPPO/MARWIL/CQL/ES/ARS/TD3 to weekly learning tests. (#18381) 3 years ago
  Sven Mika 5292b70fc6 [RLlib] Add multi-GPU attention net tests to nightly test suite (+ R2D2 tests for LSTM and attention nets). (#18368) 3 years ago
  Sven Mika e3e6ed7aaa [RLlib] Issues 17844, 18034: Fix n-step > 1 bug. (#18358) 3 years ago
  Sven Mika 9a8ca6a69d [RLlib] Fix Atari learning test regressions (2 bugs) and 1 minor attention net bug. (#18306) 3 years ago
  Sven Mika a7670d9fab [RLlib; Testing] Fix smoke-test settings for nightly `learning_tests` and `stress_test`; Add `pybullet_envs` to app-config. (#18274) 3 years ago
  Sven Mika 4888d7c9af [RLlib] Replay buffers: Add config option to store contents in checkpoints. (#17999) 3 years ago
  Sven Mika a428f10ebe [RLlib] Add multi-GPU learning tests to nightly. (#17778) 3 years ago
  Kai Fricke 10fd7111b3 [rllib] Improve test learning check, fix flaky two step qmix (#16843) 3 years ago
  Sven Mika bc09e75b78 [RLlib] Fix 3 flakey test cases. (#15785) 3 years ago
  Sven Mika e973b726c2 [RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273) 3 years ago
  Sven Mika 52c94b7ee9 [RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. (#13522) 3 years ago
  Sven Mika d49c3fae0b [RLlib] Trajectory View API: Atari framestacking. (#13315) 3 years ago
  Sven Mika 8726521604 [RLlib] JAXPolicy prep PR #2 (move get_activation_fn (backward-compatibly), minor fixes and preparations). (#13091) 3 years ago