Charles Sun
edde905741
[RLlib] Add Decision Transformer (DT) ( #27890 )
2022-08-17 13:49:13 -07:00
Artur Niederfahrenhorst
f7b4c5a7ec
[RLlib] Remove unneeded args from offline learning examples. ( #26666 )
2022-08-17 17:59:27 +02:00
Charles Sun
9330d8f244
[RLlib] Add DTTorchPolicy ( #27889 )
2022-08-17 00:28:00 -07:00
Charles Sun
61880591e9
[RLlib] Add DTTorchModel ( #27872 )
2022-08-16 18:18:29 -07:00
Charles Sun
753fad9cad
[RLlib] Add Segmentation Buffer for DT ( #27829 )
2022-08-16 15:20:41 -07:00
Sven Mika
436c89ba1a
[RLlib] Eval workers use async req manager. ( #27390 )
2022-08-16 12:05:55 +02:00
Artur Niederfahrenhorst
0dceddb912
[RLlib] Move learning_starts logic from buffers into training_step(). ( #26032 )
2022-08-11 13:07:30 +02:00
kourosh hakhamaneshi
4607e788c1
[RLlib] Fix test_ope flakiness ( #27676 )
2022-08-09 16:12:30 -07:00
kourosh hakhamaneshi
3b3c20209b
[RLlib] Fix dqn reproducibility ( #27459 )
2022-08-09 15:56:44 -07:00
kourosh hakhamaneshi
98b9fa6944
[RLlib] Hotfix for connector tests ( #27654 )
...
hot fix for rllib connector tests
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
2022-08-08 15:12:47 -07:00
kourosh hakhamaneshi
3b2a8427af
[RLlib] Fix SampleBatch to_device(). ( #27572 )
2022-08-08 18:18:33 +02:00
Jun Gong
a61095a480
[RLlib] fix bandit pre-merge tests ( #27554 )
2022-08-07 17:48:29 -07:00
Jun Gong
5f07987ab1
[RLlib] Fix connector examples ( #27583 )
2022-08-07 17:48:09 -07:00
Jun Gong
f8b2128f16
[RLlib] async_request_test needs to run exclusively. ( #27603 )
2022-08-07 17:47:29 -07:00
Rohan Potdar
5b6a58ed28
[RLlib] Add OPE Learning Tests ( #27154 )
2022-08-02 17:51:38 -07:00
Jun Gong
e6e10ce4cf
[RLlib] Revert 41c9ef70. ( #27243 )
...
Why are these changes needed?
Also:
Add validation to make sure multi-gpu and micro-batch is not used together.
Update A2C learning test to hit the microbatching branch.
Minor comment updates.
2022-07-29 11:05:15 -07:00
Jun Gong
54df8bfe42
[RLlib] Try to checkpoint a durable policy name ( #27016 )
2022-07-27 00:01:14 -07:00
kourosh hakhamaneshi
5030a4c1d3
[RLlib] Simplify agent collector ( #26803 )
2022-07-25 13:17:17 -07:00
Avnish Narayan
41c9ef709a
[RLlib] Using PG when not doing microbatching kills A2C performance. ( #26844 )
2022-07-25 15:11:26 +02:00
Jun Gong
0bc560bd54
[RLlib] Make sure we step() after adding init_obs. ( #26827 )
2022-07-21 20:43:46 -07:00
Riatre
591cd22be7
Revert "Revert "Bump pytest from 5.4.3 to 7.0.1"" ( #26525 )
...
* Revert "Revert "Bump pytest from 5.4.3 to 7.0.1""
This reverts commit ab10890e90
2022-07-18 21:21:19 -07:00
Rohan Potdar
38c9e1d52a
[RLlib]: Fix OPE trainables ( #26279 )
...
Co-authored-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
2022-07-17 14:25:53 -07:00
kourosh hakhamaneshi
569fe01096
[RLlib] improved unittests for dataset_reader and fixed bugs ( #26458 )
2022-07-17 13:38:15 -07:00
Sven Mika
4aea24c8a8
[RLlib] restart_failed_sub_environments now works for MA cases and crashes during reset(); +more tests and logging; add eval worker sub-env fault tolerance test. ( #26276 )
2022-07-15 08:55:14 +02:00
kourosh hakhamaneshi
be6e4c644f
[RLlib] Feature importance evaluation for offline RL ( #26412 )
2022-07-11 18:12:50 -07:00
Jun Gong
0c469e490e
[RLlib] Checkpoint and restore connectors. ( #26253 )
2022-07-09 01:06:24 -07:00
Avnish Narayan
1243ed62bf
[RLlib] Make Dataset reader default reader and enable CRR to use dataset ( #26304 )
...
Co-authored-by: avnish <avnish@avnishs-MBP.local.meter>
2022-07-08 12:43:35 -07:00
Jun Gong
52bb8e47d4
[RLlib] EnvRunnerV2 and EpisodeV2 that support Connectors. ( #25922 )
2022-06-30 08:44:10 +02:00
Avnish Narayan
1f9282a496
[RLlib, Offline] Make the dataset and json readers batchable ( #26055 )
...
Make the dataset and json readers batchable.
2022-06-29 11:52:40 -07:00
kourosh hakhamaneshi
f421730b47
[RLlib] Added expectation advantage_type option to CRR. ( #26142 )
2022-06-28 15:40:09 +02:00
Sven Mika
762cfbdff1
[RLlib] IMPALA and APPO metrics fixes; remove deprecated async_parallel_requests utility. ( #26117 )
2022-06-28 15:14:37 +02:00
Jun Gong
8c9cac350d
Fix unit test test_check_env.py and est_check_multi_agent.py. ( #25993 )
2022-06-23 22:55:41 -07:00
Sven Mika
96693055bd
[RLlib] More Trainer -> Algorithm renaming cleanups. ( #25869 )
2022-06-20 15:54:00 +02:00
Artur Niederfahrenhorst
a322cc5765
[RLlib] IMPALA/APPO multi-agent mix-in-buffer fixes (plus MA learning tests). ( #25848 )
2022-06-17 14:10:36 +02:00
Artur Niederfahrenhorst
f34cd2fd8f
[RLlib] Take replay buffer api example out of GPU examples. ( #25841 )
2022-06-16 19:12:38 +02:00
Yi Cheng
7b8b0f8e03
Revert "[RLlib] Remove execution plan code no longer used by RLlib. ( #25624 )" ( #25776 )
...
This reverts commit 804719876b
2022-06-14 13:59:15 -07:00
Avnish Narayan
804719876b
[RLlib] Remove execution plan code no longer used by RLlib. ( #25624 )
2022-06-14 10:57:27 +02:00
Kai Fricke
736c7b13c4
[CI] Fix team to rllib (from ml) for some replay buffer API tests. ( #25702 )
2022-06-11 18:05:16 +02:00
Sven Mika
130b7eeaba
[RLlib] Trainer to Algorithm renaming. ( #25539 )
2022-06-11 15:10:39 +02:00
Sven Mika
7c39aa5fac
[RLlib] Trainer.training_iteration -> Trainer.training_step; Iterations vs reportings: Clarification of terms. ( #25076 )
2022-06-10 17:09:18 +02:00
Artur Niederfahrenhorst
94d6c212df
[RLlib] Replay Buffer API documentation. ( #24683 )
2022-06-10 16:47:51 +02:00
Kai Fricke
aa142eb377
[RLlib; CI] Add team:rllib tag for Bazel. ( #25589 )
...
Currently, team:ml spans all ML (Tune, Train, AIR) tests and rllib tests. rllib tests are much more flaky and it would be good to split them up in the flaky test tracker. This PR changes Rllib-tests from team:ml to team:rllib to enable this separation.
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2022-06-08 22:25:59 +01:00
Sven Mika
388fb98c79
[RLlib] CRR Tests fixes. ( #25586 )
2022-06-08 19:18:55 +02:00
kourosh hakhamaneshi
4cdd508f70
[RLlib] Added CRR implementation. ( #25499 )
2022-06-08 11:42:02 +02:00
Jun Gong
9b65d5535d
[RLlib] Introduce basic connectors library. ( #25311 )
2022-06-07 19:18:14 +02:00
Rohan Potdar
a9d8da0100
[RLlib]: Doubly Robust Off-Policy Evaluation. ( #25056 )
2022-06-07 12:52:19 +02:00
Vince Jankovics
68444cd390
[tune] Custom resources per worker added to default_resource_request ( #24463 )
...
This resolves the `TODO(ekl): add custom resources here once tune supports them` item.
Also, related to the discussion [here](https://discuss.ray.io/t/reserve-workers-on-gpu-node-for-trainer-workers-only/5972/5 ).
Co-authored-by: Kai Fricke <kai@anyscale.com>
2022-06-06 22:41:02 +01:00
Jun Gong
644b80c0ef
[RLlib] mark learning and examples tests exclusive. ( #25445 )
2022-06-04 09:35:24 -07:00
Sven Mika
b5bc2b93c3
[RLlib] Move all remaining algos into algorithms directory. ( #25366 )
2022-06-04 07:35:24 +02:00
Yi Cheng
fd0f967d2e
Revert "[RLlib] Move (A/DD)?PPO and IMPALA algos to algorithms dir and rename policy and trainer classes. ( #25346 )" ( #25420 )
...
This reverts commit e4ceae19ef#25346
linux://python/ray/tests:test_client_library_integration never fail before this PR.
In the CI of the reverted PR, it also fails (https://buildkite.com/ray-project/ray-builders-pr/builds/34079#01812442-c541-4145-af22-2a012655c128 ). So high likely it's because of this PR.
And test output failure seems related as well (https://buildkite.com/ray-project/ray-builders-branch/builds/7923#018125c2-4812-4ead-a42f-7fddb344105b )
2022-06-02 20:38:44 -07:00
