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
46f6fa2361
[RLlib] Example script for restoring 1 agent (out of n) from a checkpoint (multi-agent). ( #15540 )
2021-05-10 16:09:05 +02:00
Eric Liang
ff36ae594b
Remove flaky tag from newly unflaky tests ( #15639 )
2021-05-05 12:15:46 -07:00
Kai Fricke
1d52ab819f
[release] release 1.3.0 results and test updates ( #15366 )
...
Convert a number of release tests and add logs for release 1.3.0
2021-05-04 22:10:04 +01:00
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
mvindiola1
170366fbf1
[RLlib] contrib/MADDPG: Make get_weights and set_weights use dictionaries rather than lists. ( #14903 )
...
Co-authored-by: Manny Vindiola <manuel.m.vindiola.civ@mail.mil>
2021-05-04 13:26:39 +02:00
Sertingolix
5a45009ebc
[RLlib] Handle array custom metrics correctly in evaluate ( #15190 )
...
Co-authored-by: Lucas Brunner <lucas.brunner@urb-x.ch>
2021-05-04 13:25:28 +02:00
Antoine Galataud
ce1c001b1d
[RLlib] DQN: Place LearningRateSchedule mixin at the right moment ( #15558 )
2021-05-04 13:21:40 +02:00
Yeachan-Heo
0552f6e886
[RLlib] Update alpha_zero_policy.py ( #15042 )
2021-05-04 13:20:24 +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
fc3a65f9d4
[RLlib] Split test_checkpoint_restore tests into 3 and make each "large" (from "enormous"). ( #15499 )
2021-04-30 12:33:12 +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
Eric Liang
af01a47d59
Add support for tune,serve,rllib tests to flaky builder ( #15447 )
2021-04-22 15:03:29 -07:00
Sven Mika
b9761d7081
[RLlib] Discussion 1759: SampleBatch._get_slice_indices stuck for R2D2 when using incorrect Trainer. ( #15451 )
...
Thanks @Manuscrit for raising this issue!
2021-04-22 19:21:03 +02:00
Sven Mika
7e1a191f17
[RLlib] Remove all remaining tf- and MuJoCo warnings from RLlib. ( #15454 )
2021-04-22 19:20:19 +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
SangBin Cho
1d87e4447d
[Test] increase the test size of test io that consistenly times out ( #15341 )
2021-04-15 14:02:41 -07:00
Sven Mika
8b3554e37e
[RLlib] Remove all (already soft-deprecated) SampleBatch.data from code. ( #15335 )
2021-04-15 19:19:51 +02:00
Sven Mika
c90de315e5
[RLlib] APEX returns incorrect default resources (PleacementGroupFactory) colocated missing replay actors. ( #15295 )
2021-04-15 16:50:42 +01:00
Sven Mika
e961d2f4b2
[RLlib] Improve example scripts for attention nets, CartPole LSTM, and custom RNN-models. ( #15329 )
2021-04-15 16:11:34 +02:00
Sven Mika
45d6560759
[RLlib] Fix flakey custom_fast_model_torch/tf tests. ( #15330 )
2021-04-15 16:10:29 +02:00
SangBin Cho
27ab0c7633
[Test] Skip the failing rllib example test. ( #15321 )
2021-04-14 20:19:44 -07:00
Sven Mika
bbfa8ffec9
[RLlib] Minor release 1.3 warnings cleanups. ( #15272 )
2021-04-14 14:03:15 +02:00
Sven Mika
ef0f163d16
[RLlib] Discussion 1709: IMPALA (tf and torch) reports sum of entropy (over batch) in stats. Should report mean instead. ( #15290 )
2021-04-14 11:44:25 +02:00
Sven Mika
5254d2fb36
[RLlib] Support parallelizing evaluation and training (optional). ( #15040 )
2021-04-13 09:53:35 +02:00
Sven Mika
9c5a0cfd7a
[RLlib] Issue 14385: Policy.compute_actions_from_input_dict does not properly track accessed fields for Policy's view requirements. ( #14386 )
2021-04-11 18:20:04 +02:00
Sven Mika
dfc116ea27
[RLlib] Discussion 681: Metrics prepends newest episodes instead of appending. ( #15236 )
2021-04-11 15:31:43 +02:00
Sven Mika
1c9701e9cb
[RLlib] Discussion 1513: on_episode_step() callback called after very first reset (should not). ( #15218 )
2021-04-11 13:16:17 +02:00
Sven Mika
b267f1f1ba
[RLlib] Add support for Int-Box action spaces. ( #15012 )
2021-04-11 13:16:01 +02:00
Dmitri Gekhtman
58fbb419ea
[client][rllib] Add client_mode_hook for ray.get_gpu_ids ( #15185 )
2021-04-08 23:36:11 -07:00
Yi Cheng
e552e3f19c
Skip test_dependency_torch ( #15123 )
2021-04-05 18:02:10 -07:00
Kai Fricke
d33b0e4bc3
[tune] Reconcile placement groups every N seconds to avoid bottlenecks when running many short trials ( #15011 )
...
Closes a release blocking issue
2021-04-01 17:04:44 +02:00
Sven Mika
1bb70e4907
[RLlib] Issue 14523: Torch + py3.8 leads to GPU device error. ( #15014 )
2021-03-30 21:43:11 +02:00
Sven Mika
95686a8fdd
[RLlib] Issue 14533: Tf-eager properly use tree.map_struct on value of type Repeated (RLlib-specific space) ( #15015 )
2021-03-30 19:28:45 +02:00
