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 |