Kai Fricke
34cf5db109
[tune] Fix hyperopt points to evaluate for nested lists ( #18113 )
2021-08-26 14:34:22 +02:00
Sven Mika
8acb469b04
[RLlib; Testing] Green all RLlib nightly tests. ( #18073 )
2021-08-26 14:09:20 +02:00
gjoliver
a8813675f4
[RLlib] Issue 17900: Set seed in single vectorized sub-envs properly, if num_envs_per_worker > 1 ( #18110 )
...
* In case a worker runs multiple envs, make sure a different seed can be deterministically set on all of them.
* Revert a couple of whitespace changes.
* Fix a few style errors.
Co-authored-by: Jun Gong <jungong@mbpro.local>
2021-08-26 11:32:58 +02:00
Sven Mika
b6aa8223bc
[RLlib] Fix final_scale's default value to 0.02 (see OrnsteinUhlenbeck exploration). ( #18070 )
2021-08-25 14:22:09 +02:00
Sven Mika
9883505e84
[RLlib] Add [LSTM=True + multi-GPU]-tests to nightly RLlib testing suite (for all algos supporting RNNs, except R2D2, RNNSAC, and DDPPO). ( #18017 )
2021-08-24 21:55:27 +02:00
Sven Mika
ff7740e508
[RLlib] Fix the git-bisect helper/debugging script. ( #18040 )
2021-08-24 18:08:29 +02:00
Sven Mika
494ddd98c1
[RLlib] Replace "seq_lens" w/ SampleBatch.SEQ_LENS. ( #17928 )
2021-08-21 17:05:48 +02:00
simonsays1980
60aee4a330
[RLlib] Add example script for bare metal Policy with custom view_requirements. ( #17896 )
2021-08-20 12:17:13 +02:00
Sven Mika
8248ba531b
[RLlib] Redo #17410 : Example script: Remote worker envs with inference done on main node. ( #17960 )
2021-08-20 08:02:18 +02:00
Alex Wu
318ba6fae0
Revert "[RLlib] Add example script for how to have n remote (parallel) envs with inference happening on "main" (possibly GPU) node. ( #17410 )" ( #17951 )
...
This reverts commit 8fc16b9a18
2021-08-19 07:55:10 -07:00
Sven Mika
8fc16b9a18
[RLlib] Add example script for how to have n remote (parallel) envs with inference happening on "main" (possibly GPU) node. ( #17410 )
2021-08-19 12:14:50 +02:00
Clark Zinzow
d958457d07
[Core] Second pass at privatizing APIs. ( #17885 )
...
* gcs_utils
* resource_spec
* profiling
* ray_perf and ray_cluster_perf
* test_utils
2021-08-18 20:56:33 -07:00
Simon Mo
b573864928
[CI] Add test owners ( #17893 )
2021-08-18 18:38:31 -07:00
Kai Fricke
bf3eaa9264
[RLlib] Dreamer fixes and reinstate Dreamer test. ( #17821 )
...
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-08-18 18:47:08 +02:00
Sven Mika
a428f10ebe
[RLlib] Add multi-GPU learning tests to nightly. ( #17778 )
2021-08-18 17:21:01 +02:00
Sven Mika
f18213712f
[RLlib] Redo: "fix self play example scripts" PR (17566) ( #17895 )
...
* wip.
* wip.
* wip.
* wip.
* wip.
* wip.
* wip.
* wip.
* wip.
2021-08-17 09:13:35 -07:00
Chris Bamford
58a73821fb
[RLlib] IMPALA sample throughput calculation and full queue slowdown fixes ( #17822 )
2021-08-17 14:01:41 +02:00
simonsays1980
7b33dc21dc
[RLlib] Fix update model view requirements from init state for bare-metal policies with custom view-reqs. ( #17867 )
...
* Changed '_update_model_view_requirements_from_init_state()' to adopt the 'shift' in view_requirements from a user-defined policy that inherits directly from Policy.
* Added slightly modifed version of Sven's suggestion. Like this any user-defined attributes of the ViewRequirement of the state get conserved.
* I saw that the code in _update_model_view_requirements_from_init_state() had changed and is not identical to my locally installed version. In the new version view_requirements from the model and the policy get united and therefore a loop runs through this unified list. Code should run now in the present version
* Apply suggestions from code review
2021-08-17 11:49:24 +02:00
Thomas Lecat
c02f91fa2d
[RLlib] Ape-X doesn't take the value of prioritized_replay into account ( #17541 )
2021-08-16 22:18:08 +02:00
Stefan Schneider
eab9c25856
[RLlib] Better example scripts: Description --no-tune and --local-mode CLI options (autoregressive_action_dist.py) ( #17705 )
2021-08-16 22:08:13 +02:00
Sven Mika
f3bbe4ea44
[RLlib] Test cases/BUILD cleanup; split "everything else" (longest running one rn) tests in 2. ( #17640 )
2021-08-16 22:01:01 +02:00
Ian Rodney
2f200e5c2b
[Client] Pass ray.init() args to the remote server ( #17776 )
2021-08-16 12:34:01 -07:00
dependabot[bot]
91d01f7211
[RLlib](deps): Bump tensorflow from 2.4.1 to 2.5.0 in /python/requirements/rllib ( #15849 )
2021-08-16 10:55:48 +02:00
Sven Mika
2bd2ee7a73
[RLlib] SampleBatch: Docstring- and API cleanups; Add support for nested data. ( #17485 )
2021-08-16 06:08:14 +02:00
Sven Mika
c2ea2c01bb
[RLlib] Redo: Add support for multi-GPU to DDPG. ( #17789 )
...
* wip.
* wip.
* wip.
* wip.
* wip.
* wip.
2021-08-13 18:01:24 -07:00
akern40
0cb2c602db
[rllib] Fixes typo in RolloutWorker.__init__ ( #17583 )
...
Fixes the typo in RolloutWorker.__init__, closes #17582
2021-08-13 13:17:36 -07:00
mguarin0
3e010c5760
[rllib] bug fix for rllib pettingzoo pistonball_v4 example ( #17701 )
...
* bug fix for rllib pettingzoo pistonball_v4 example
* adding test for PR 17701
* ran scripts/format.sh
* ok
Signed-off-by: Richard Liaw <rliaw@berkeley.edu>
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2021-08-12 00:25:00 -07:00
Sven Mika
7f2b3c0824
[RLlib] Issue 17667: CQL-torch + GPU not working (due to simple_optimizer=False; must use simple optimizer!). ( #17742 )
2021-08-11 18:30:21 +02:00
Julius Frost
6891dee6ea
[RLlib] Better exceptions with traceback in TorchPolicy ( #17690 )
2021-08-11 15:01:07 +02:00
Sven Mika
811d71b368
[RLlib] Issue 17653: Torch multi-GPU (>1) broken for LSTMs. ( #17657 )
2021-08-11 12:44:35 +02:00
Sven Mika
29f20cccb6
[RLlib] Issue 17706: AttributeError: 'numpy.ndarray' object has no attribute 'items'" on certain turn-based MultiAgentEnvs with Dict obs space. ( #17735 )
2021-08-11 12:33:35 +02:00
J K Terry
48e32555c8
[rllib] Update PettingZoo dependency versions ( #17702 )
...
* update pettingzoo dependency versions
* pettingzoo verison
* fix tests
2021-08-11 01:19:19 -07:00
Julius Frost
9322f6aab5
[rllib] Fix classes decorated with @Deprecated to be classes instead of methods ( #17666 )
...
* fix deprecated classes from being methods
* format
2021-08-10 18:25:31 -07:00
Amog Kamsetty
0b8489dcc6
Revert "[RLlib] Add support for multi-GPU to DDPG. ( #17586 )" ( #17707 )
...
This reverts commit 0eb0e0ff58
2021-08-10 10:50:21 -07:00
Amog Kamsetty
77f28f1c30
Revert "[RLlib] Fix Trainer.add_policy for num_workers>0 (self play example scripts). ( #17566 )" ( #17709 )
...
This reverts commit 3b447265d8
2021-08-10 10:50:01 -07:00
Sven Mika
3b447265d8
[RLlib] Fix Trainer.add_policy for num_workers>0 (self play example scripts). ( #17566 )
2021-08-05 11:41:18 -04:00
Sven Mika
0eb0e0ff58
[RLlib] Add support for multi-GPU to DDPG. ( #17586 )
2021-08-05 11:39:51 -04:00
Sven Mika
3013d9b341
[RLlib] Fix "Cannot convert a symbolic Tensor (default_policy/strided_slice_3:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported" ( #17587 )
2021-08-05 11:39:15 -04:00
Kai Fricke
5d56a8aac5
[RLlib] Fix ignoring "sample_collector" config key ( #17460 )
2021-08-04 10:27:35 -04:00
Sven Mika
b539560429
[RLlib] Remove SampleBatch._get_slice_indices() deprecated logging spam (moderate). ( #17567 )
2021-08-04 04:21:32 -04:00
Sven Mika
5107d16ae5
[RLlib] Add @Deprecated decorator to simplify/unify deprecation of classes, methods, functions. ( #17530 )
2021-08-03 18:30:02 -04:00
Sven Mika
924f11cd45
[RLlib] Torch algos use now-framework-agnostic MultiGPUTrainOneStep execution op (~33% speedup for PPO-torch + GPU). ( #17371 )
2021-08-03 11:35:49 -04:00
Sven Mika
8a844ff840
[RLlib] Issues: 17397, 17425, 16715, 17174. When on driver, Torch|TFPolicy should not use ray.get_gpu_ids() (b/c no GPUs assigned by ray). ( #17444 )
2021-08-02 17:29:59 -04:00
Kai Fricke
44d209dd5f
[tune] re-enable tensorboardx without torch installed ( #17403 )
2021-07-29 10:39:38 +01:00
kk-55
a7f8dc9d77
[RLlib] New and changed version of parametric actions cartpole example + small suggested update in policy_client.py ( #15664 )
2021-07-28 15:25:09 -04:00
Julius Frost
d7a5ec1830
[RLlib] SAC tuple observation space fix ( #17356 )
2021-07-28 12:39:28 -04:00
Sven Mika
0d8fce8fd8
[RLlib] Discussion 2294: Custom vector env example and fix. ( #16083 )
2021-07-28 10:40:04 -04:00
Rohan138
f30b444bac
[Rllib] set self._allow_unknown_config ( #17335 )
...
Co-authored-by: Sven Mika <sven@anyscale.io>
2021-07-28 11:48:41 +01:00
Sven Mika
58da5c1c9b
[RLlib] Discussion 3001: Fix comment on internal state shape (must be [B x S=state dim]). ( #17341 )
2021-07-27 21:41:53 -04:00
Sven Mika
90b21ce27e
[RLlib] De-flake 3 test cases; Fix config.simple_optimizer and SampleBatch.is_training warnings. ( #17321 )
2021-07-27 14:39:06 -04:00
