Sven Mika
55a90e670a
[RLlib] Trainer.add_policy() not working for tf, if added policy is trained afterwards. ( #16927 )
2021-07-11 23:41:38 +02:00
Julius Frost
a88b217d3f
[rllib] Enhancements to Input API for customizing offline datasets ( #16957 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2021-07-10 15:05:25 -07:00
Sven Mika
7862dd64ea
[RLlib] Fix bug in policy.py: normalize_actions=True has to call unsquash_action, not normalize_action. ( #16774 )
2021-07-08 17:31:34 +02:00
Sven Mika
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes ( #16531 )
2021-06-30 12:32:11 +02:00
AnnaKosiorek
1e709771b2
[rllib][minor] clarification of the softmax axis in dqn_torch_policy ( #16311 )
...
pytorch nn.functional.softmax (unlike tf.nn.softmax) calculates softmax along zeroth dimension by default
2021-06-26 11:19:54 -07:00
Sven Mika
c95dea51e9
[RLlib] External env enhancements + more examples. ( #16583 )
2021-06-23 09:09:01 +02:00
Sven Mika
be6db06485
[RLlib] Re-do: Trainer: Support add and delete Policies. ( #16569 )
2021-06-21 13:46:01 +02:00
Sven Mika
169ddabae7
[RLlib] Issue 15973: Trainer.with_updates(validate_config=...) behaves confusingly. ( #16429 )
2021-06-19 22:42:00 +02:00
Amog Kamsetty
bd3cbfc56a
Revert "[RLlib] Allow policies to be added/deleted on the fly. ( #16359 )" ( #16543 )
...
This reverts commit e78ec370a9
2021-06-18 12:21:49 -07:00
Sven Mika
2900a06dd7
[RLlib] Issue 14503: SAC not allowing custom action distributions. ( #16427 )
2021-06-18 17:27:29 +02:00
Sven Mika
e78ec370a9
[RLlib] Allow policies to be added/deleted on the fly. ( #16359 )
2021-06-18 10:31:30 +02:00
Sven Mika
d0014cd351
[RLlib] Policies get/set_state fixes and enhancements. ( #16354 )
2021-06-15 13:08:43 +02:00
Chris Bamford
fd1a97e39f
[RLlib] Memory leak docs ( #15908 )
2021-06-10 18:10:21 +02:00
Sven Mika
3d4dc60e2e
[RLlib] CQL iteration count fixes: Remove dummy buffer and unnecessary store op from exec_plan. ( #16332 )
2021-06-10 07:49:17 +02:00
Sven Mika
e2be41b407
[RLlib] MARWIL + BC: Various fixes and enhancements. ( #16218 )
2021-06-03 22:29:00 +02:00
Sven Mika
5fe34862ce
[RLlib] DDPG torch GPU bug. ( #16133 )
2021-05-28 22:09:25 +02:00
Sven Mika
33a69135cb
[RLlib] Issue 16117: DQN/APEX torch not working on GPU. ( #16118 )
2021-05-28 09:12:53 +02:00
Sven Mika
f6302d81be
[RLlib] Discussion 2210: BC algo broken, if "advantages" missing in offline data. ( #16019 )
2021-05-25 08:47:17 +02:00
Sven Mika
e80095591c
[RLlib] Entropy coeff schedule bug fix and git bisect script. ( #15937 )
2021-05-20 18:15:10 +02:00
Sven Mika
2d34216660
[RLlib] APEX-DQN: Bug fix for torch and add learning test. ( #15762 )
2021-05-20 09:27:03 +02:00
Sven Mika
eaa7f6696d
[RLlib] Issue 15887: MARWIL adv norm update mismatch for tf (static-graph) vs torch versions. ( #15898 )
2021-05-19 15:44:11 -07:00
Michael Luo
474f04e322
[RLlib] DDPG/TD3 + A3C/A2C + MARWIL/BC Annotation/Comments/Code Cleanup ( #14707 )
2021-05-19 16:32:29 +02:00
Chris Bamford
0be83d9a95
[RLlib] Fixing Memory Leak In Multi-Agent environments. Adding tooling for finding memory leaks in workers. ( #15815 )
2021-05-18 13:23:00 +02:00
Sven Mika
2303851c3c
[RLlib] Torch multi-GPU + LSTM/RNN bug fix. ( #15492 )
2021-05-18 11:51:05 +02:00
Sven Mika
839fc59224
[RLlib] CQL TensorFlow support ( #15841 )
2021-05-18 11:10:46 +02:00
Sven Mika
d89fb82bfb
[RLlib] Add simple curriculum learning API and example script. ( #15740 )
2021-05-16 17:35:10 +02:00
Sven Mika
469f5227da
[RLlib] CQL bug fix: Normalize actions for atanh in BC part of the CQL loss. ( #15814 )
2021-05-16 15:21:06 +02:00
Sven Mika
bc09e75b78
[RLlib] Fix 3 flakey test cases. ( #15785 )
2021-05-16 12:20:33 +02:00
Sven Mika
c4a3e1589b
[RLlib] CQL: Bug fixes and OPE example added to test and offline_rl.py example. ( #15761 )
2021-05-13 09:17:23 +02:00
Sven Mika
16ddab49f5
[RLlib] Trainer._evaluate -> Trainer.evaluate; Also make evaluation possible w/o evaluation worker set. ( #15591 )
2021-05-12 12:16:00 +02:00
Sven Mika
a495759f06
[RLlib] Discussion 2022: PPO should auto-adjust rollout_fragment_length if other settings do not align with train_batch_size. ( #15611 )
2021-05-10 16:16:02 +02:00
Sven Mika
461d73ddf1
[RLlib] simple_optimizer should not be used by default for tf+MA. ( #15365 )
2021-05-10 16:10:44 +02:00
Sven Mika
c7563a32ed
[RLlib] DD-PPO not supported on Win (add meaningful error message). ( #15631 )
2021-05-04 19:26:17 +02:00
Michael Luo
4cbe13cdfd
[RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. ( #15603 )
...
Co-authored-by: Sven Mika <sven@anyscale.io>
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-05-04 19:06:19 +02:00
Sven Mika
4b3add0066
[RLlib] Discussion 2021: PPO does not learn vf, iff use_gae=False (ignores use_critic setting). ( #15610 )
2021-05-04 14:17:00 +02:00
Antoine Galataud
ce1c001b1d
[RLlib] DQN: Place LearningRateSchedule mixin at the right moment ( #15558 )
2021-05-04 13:21:40 +02:00
Amog Kamsetty
ebc44c3d76
[CI] Upgrade flake8 to 3.9.1 ( #15527 )
...
* formatting
* format util
* format release
* format rllib/agents
* format rllib/env
* format rllib/execution
* format rllib/evaluation
* format rllib/examples
* format rllib/policy
* format rllib utils and tests
* format streaming
* more formatting
* update requirements files
* fix rllib type checking
* updates
* update
* fix circular import
* Update python/ray/tests/test_runtime_env.py
* noqa
2021-05-03 14:23:28 -07:00
Sven Mika
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. ( #15273 )
2021-04-30 19:26:30 +02:00
Sven Mika
78b776942f
[RLlib] Discussion 1928: Initial lr wrong if schedule used that includes ts=0 (both tf and torch). ( #15538 )
2021-04-27 17:19:52 +02:00
SebastianBo1995
f5be8d8f74
[Rllib] Offline Learning Bug, different shapes ( #15132 )
2021-04-27 17:18:17 +02:00
Sven Mika
bb8a286cbc
[RLlib] Support native tf.keras.Model (milestone toward obsoleting ModelV2 class). ( #14684 )
2021-04-27 10:44:54 +02:00
Kai Fricke
2c11a1aff1
[RLlib] Evaluation parallel to training check, key-error hotfix ( #15345 )
2021-04-27 08:38:10 +02:00
mvindiola1
9330403200
[RLlib] Mask out padded values for A3C loss with recurrent policy ( #15525 )
2021-04-27 08:36:04 +02:00
Sven Mika
354c960fff
[RLlib] Fix test_dependency_torch and fix custom logger support for RLlib. ( #15120 )
2021-04-24 08:13:41 +02:00
Sven Mika
bdda73e2dd
[RLlib] Torch multi-GPU bug fixes (discussion 1755). ( #15421 )
...
Thanks a lot @Bam4d for raising this and your help on fixing the worker GPU issue for torch!
2021-04-22 11:29:42 +02:00
Sven Mika
7318439c3d
[RLlib] DQN native_ratio (for training intensity) incorrect (discussion 1763). ( #15436 )
...
Thanks @Manuscrit !
2021-04-22 11:06:29 +02:00
Fabien Couthouis
fe06642df0
[RLlib] Report mean losses instead of sum in IMPALA (discussion 1709) ( #15427 )
2021-04-21 10:59:06 +02:00
Sven Mika
7ff27dfe07
[RLlib] Remove atari dependency for RLlib (in favor of detailed error message). ( #15292 )
2021-04-20 08:46:58 +02:00
Sven Mika
41968512ca
[RLlib] Partial GPU examples (for learner and workers). ( #15334 )
2021-04-20 08:46:05 +02:00
Sven Mika
cecfc3b43b
[RLlib] Multi-GPU support for Torch algorithms. ( #14709 )
2021-04-16 09:16:24 +02:00
