Jun Gong
ca5e0dcaf4
[RLLib] Record framework and algorithm used by an RLlib run. ( #26956 )
...
Automatically record framework and algorithm used by RLlib jobs.
For better planning.
2022-07-25 16:16:36 -07:00
kourosh hakhamaneshi
5030a4c1d3
[RLlib] Simplify agent collector ( #26803 )
2022-07-25 13:17:17 -07:00
Artur Niederfahrenhorst
b1594260ba
[RLlib] Small SlateQ example fix. ( #26948 )
2022-07-25 15:12:42 +02:00
Avnish Narayan
41c9ef709a
[RLlib] Using PG when not doing microbatching kills A2C performance. ( #26844 )
2022-07-25 15:11:26 +02:00
Artur Niederfahrenhorst
e9a8f7d9ae
[RLlib] Unify gnorm mixin for tf and torch policies. ( #26102 )
2022-07-24 15:31:09 +02:00
Ishant Mrinal
b32c784c7f
[RLLib] RE3 exploration algorithm TF2 framework support ( #25221 )
2022-07-23 18:05:01 -07:00
Rohan Potdar
a53bbe49bf
[RLlib]: Raise deprecation warning in MARWIL OPE methods. ( #26893 )
2022-07-23 13:55:40 +02:00
Rohan Potdar
97bcf38ec0
[RLlib] Fix torch None conversion in torch_utils.py::convert_to_torch_tensor. ( #26863 )
2022-07-23 13:54:57 +02:00
Rohan Potdar
69f6b843da
[RLlib] Test output length in DatasetReader with default IOContext. ( #26852 )
2022-07-23 13:53:59 +02:00
Rohan Potdar
2f22262d39
[RLlib]: Fix SampleBatch.split_by_episode to use dones if episode id is not available ( #26492 )
2022-07-22 16:46:05 -07:00
Steven Morad
259429bdc3
Bump gym dep to 0.24 ( #26190 )
...
Co-authored-by: Steven Morad <smorad@anyscale.com>
Co-authored-by: Avnish <avnishnarayan@gmail.com>
Co-authored-by: Avnish Narayan <38871737+avnishn@users.noreply.github.com>
2022-07-22 12:37:16 -07:00
Avnish Narayan
2a0ef663c9
[rllib] Use compress observations where replay buffers and image obs are used in tuned examples ( #26735 )
2022-07-22 10:10:51 -07:00
Fabian Witter
dc2ad6c8b4
[RLlib] Fix ModelCatalog for nested complex inputs ( #25620 )
2022-07-22 00:45:25 -07:00
Jun Gong
6c1acd1a2f
[RLlib] Quick state buffer connector fix ( #26836 )
2022-07-21 20:43:59 -07:00
Jun Gong
0bc560bd54
[RLlib] Make sure we step() after adding init_obs. ( #26827 )
2022-07-21 20:43:46 -07:00
Rohan Potdar
2b13ac85f9
[RLLib]: Make IOContext optional for DatasetReader ( #26694 )
2022-07-21 13:05:00 -07:00
Olaf Lipinski
8271406a04
[RLLib] Fix MultiDiscrete not being one-hotted correctly ( #26558 )
...
Co-authored-by: Jun Gong <jungong@anyscale.com>
2022-07-20 15:25:53 -07:00
kourosh hakhamaneshi
aec79afda1
[RLlib] Fixes CRR flakeyness ( #26770 )
2022-07-20 12:08:57 -07:00
Avnish Narayan
9063cc9d5e
[RLlib] Fix memory leak in APEX_DQN ( #26691 )
2022-07-19 16:16:24 -07:00
Avnish Narayan
af41f21be0
[RLlib] Make queue placement ops blocking ( #26581 )
...
Signed-off-by: avnish avnish@anyscale.com
This change should fix issues with IMPALA and potentially APEX that stem from the various learner threads
Signed-off-by: avnish <avnish@anyscale.com>
2022-07-19 20:07:36 +01:00
Jun Gong
6b6d3017ba
[RLlib] more connector polishes and fixes. ( #26645 )
2022-07-19 08:50:28 -07:00
Rohan Potdar
4fded80813
[RLlib]: Fix FQE Policy call ( #26671 )
2022-07-19 00:58:31 -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
Artur Niederfahrenhorst
0ce3bc5e48
[RLlib] Add/reorder Args of Prioritized/MixIn MultiAgentReplayBuffer. ( #26428 )
2022-07-18 18:04:03 +02:00
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
Ishant Mrinal
57244aeee3
[RLlib] Make DQN update_target use only trainable variables. ( #25226 )
2022-07-15 09:17:06 +02:00
mgerstgrasser
f0e9d1a9bb
[RLlib] In env check, step only expected agents. ( #26425 )
2022-07-15 09:16:09 +02:00
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
Avnish Narayan
a322ac463c
[RLlib] Make JSONReader default, users will have to use the DatasetReader for any speedups. ( #26541 )
2022-07-14 17:19:38 +02:00
Jun Gong
104407a6e5
[RLlib] Fix all the erroneous on_trainer_init warning. ( #26433 )
2022-07-13 18:56:01 +02:00
Jun Gong
b383d987d1
[RLlib] Fix a bunch of issues related to connectors. ( #26510 )
2022-07-13 18:55:20 +02:00
Avnish Narayan
5df66b917d
[Lint Check] Remove broken link ( #26505 )
...
The paper is not available anymore.
2022-07-13 10:30:20 +01:00
Christy Bergman
7c925fe99f
[RLlib; docs] Re-organize algorithms so TOC matches README. ( #26339 )
2022-07-13 10:46:36 +02:00
Ram Rachum
14800e5ac7
Fix exception cause in preprocessors.py ( #26322 )
2022-07-12 20:15:04 -07:00
Rohan Potdar
09ce4711fd
[RLlib]: Move OPE to evaluation config ( #25911 )
2022-07-12 11:04:34 -07:00
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
Jun Gong
d234348bd2
[RLlib] Minor simplification of code. ( #26312 )
2022-07-08 13:21:54 -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
Kai Fricke
e1a7efe148
[tune] Use Checkpoint.to_bytes() for store_to_object ( #25805 )
...
We currently use our own serialization to ship checkpoints as objects. Instead we should use the Checkpoint class. This PR also adds support to create results from checkpoints pointing to object references.
Depends on #26351
Signed-off-by: Kai Fricke <kai@anyscale.com>
2022-07-08 18:01:20 +01:00
Steven Morad
0bc465f687
[RLlib] Fix docstring and add unit tests for rnn sequencing. ( #26197 )
2022-07-06 14:32:57 +02:00
Jun Gong
34d1e580cb
[rllib/docs] Minor import doc fix. ( #26269 )
2022-07-02 06:52:38 -07:00
Amog Kamsetty
60a9dc0a5c
[rllib] Add __init__.py file to rllib.conncectors ( #26238 )
...
__init__.py file is needed for this package to be included in the Ray wheels
2022-06-30 13:54:49 -07:00
Sven Mika
f8785c49df
[RLlib] Issue 25696: Output writers not working w/ multiple workers. ( #25722 )
2022-06-30 13:25:56 +02:00
Sven Mika
ca913ff6d6
[RLlib] Eval WorkerSet crashes when trying to re-add a failed worker (eval set does not have local worker). ( #26134 )
2022-06-30 13:25:22 +02:00
Jun Gong
d83bbda281
[RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. ( #25954 )
2022-06-30 11:38:21 +02:00
Jun Gong
52bb8e47d4
[RLlib] EnvRunnerV2 and EpisodeV2 that support Connectors. ( #25922 )
2022-06-30 08:44:10 +02:00
Christy Bergman
541e2ec14c
Add Environments to Key Concepts page ( #25791 )
2022-06-29 16:10:49 -07:00
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
