Corey Lowman
668ea0bc26
Fix typo RMSProp -> RMSprop ( #13063 )
2020-12-23 13:37:46 -08:00
Sven Mika
1e74187179
[RLlib] TorchPolicies: Accessing "infos" dict in train_batch causes TypeError. ( #13039 )
2020-12-23 11:30:50 -05:00
Sven Mika
670d083a56
[RLlib] Fix broken unity3d_env import in example server script. ( #13040 )
2020-12-23 11:29:58 -05:00
Sven Mika
01faeabc17
[RLlib] Issue 12789: RLlib throws the warning "The given NumPy array is not writeable" ( #12793 )
2020-12-22 09:28:07 -05:00
Sven Mika
d5604eaba3
[RLlib] Attention nets PyTorch support and cleanup (using traj. view API). ( #12029 )
2020-12-21 18:38:34 -08:00
roireshef
ef95db51e1
[RLlib] Arbitrary input to value() when not using GAE ( #12941 )
2020-12-21 12:19:33 -05:00
Sven Mika
b2bcab711d
[RLlib] Attention Nets: tf ( #12753 )
2020-12-20 20:22:32 -05:00
Sven Mika
407a3523f3
[RLlib] eval_workers after restore not generated in Trainer due to unintuitive config handling. ( #12844 )
2020-12-20 09:37:31 -05:00
Sven Mika
124c8318a8
[RLlib] Fix broken test_distributions.py (test_categorical) ( #12915 )
2020-12-17 17:44:26 -06:00
Edward Oakes
aedcf0c9d9
Disable test_distributions ( #12919 )
2020-12-16 14:17:49 -08:00
Edward Oakes
cde711aaf1
Revert "[RLLib] Execution-Folder Type Annotations ( #12760 )" ( #12886 )
...
This reverts commit becca1424d
2020-12-15 11:03:02 -08:00
Michael Luo
becca1424d
[RLLib] Execution-Folder Type Annotations ( #12760 )
2020-12-14 19:16:44 +01:00
Sven Mika
3c808835a5
[RLlib] Issue 12831: AttributeError: 'NoneType' object has no attribute 'id' when using custom Atari env. ( #12832 )
2020-12-13 16:15:54 +01:00
Sven Mika
abb1eefdc2
[RLlib] Issue 12483: Discrete observation space error: "ValueError: ('Observation ({}) outside given space ..." when doing Trainer.compute_action. ( #12787 )
2020-12-11 22:43:30 +01:00
Sven Mika
74c98ac38e
[RLlib] Issue 12244: Unable to restore multi-agent PPOTFPolicy's Model (from exported). ( #12786 )
2020-12-11 16:13:38 +01:00
Sven Mika
a082ea18b8
[RLlib] Issue 12212: "TFEagerPolicy has no attribute action_sampler_fn.
2020-12-11 12:57:33 +01:00
Sven Mika
deb33bce84
[RLlib] Add DQN SoftQ learning test case. ( #12712 )
2020-12-10 14:55:19 +01:00
Sven Mika
ea25482f6a
WIP. ( #12706 )
2020-12-09 11:49:21 -08:00
Sven Mika
f6241302a8
[RLlib] Fix issue 12678: MultiAgentBatch has no attribute total. ( #12704 )
2020-12-09 16:41:13 +01:00
Sven Mika
28108c905b
[RLlib] Tf-eager policy bug fix: Duplicate model call in compute_gradients. ( #12682 )
2020-12-09 08:03:58 +01:00
Sven Mika
e40b14d255
[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. ( #12420 )
2020-12-08 16:41:45 -08:00
Felipe Antunes
4c0f0ce3a9
[RLlib] In OffPolicyEstimators (Offline RL): Include last step of trajectory ( #12619 )
2020-12-08 12:39:40 +01:00
Sven Mika
340b1e99fc
[RLlib] Fix JAX import bug. ( #12621 )
2020-12-07 11:05:08 -08:00
Sven Mika
99c81c6795
[RLlib] Attention Net prep PR #3 . ( #12450 )
2020-12-07 13:08:17 +01:00
Kai Fricke
219c445648
[tune] verbosity refactor second attempt ( #12571 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2020-12-04 13:56:26 -08:00
Sven Mika
3f4bc16276
[RLlib] Add a minimal JAX ModelV2 (FCNet) to RLlib. ( #12502 )
2020-12-03 15:51:30 +01:00
Sven Mika
19c8033df2
[RLlib] Fix most remaining RLlib algos for running with trajectory view API. ( #12366 )
...
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* LINT and fixes.
MB-MPO and MAML not working yet.
* wip
* update
* update
* rmeove
* remove dep
* higher
* Update requirements_rllib.txt
* Update requirements_rllib.txt
* relpos
* no mbmpo
Co-authored-by: Eric Liang <ekhliang@gmail.com>
2020-12-01 17:41:10 -08:00
Sven Mika
9021f15b2a
[RLlib] Fix setup-dev.py error when creating a softlink for new_dashboard. ( #12442 )
2020-12-01 11:46:59 +01:00
Sven Mika
3ad9365e1d
[RLlib] Attention Net prep PR #2 : Smaller cleanups. ( #12449 )
2020-12-01 08:21:45 +01:00
Amog Kamsetty
f9a99f20dd
Revert "Re-Revert "[Core] zero-copy serializer for pytorch ( #12344 )" ( #12478 )" ( #12515 )
...
This reverts commit 3f22448834
2020-11-30 19:05:55 -08:00
Siyuan (Ryans) Zhuang
3f22448834
Re-Revert "[Core] zero-copy serializer for pytorch ( #12344 )" ( #12478 )
...
* [Core] zero-copy serializer for pytorch (#12344 )
* zero-copy serializer for pytorch
* address possible bottleneck
* add tests & device support
(cherry picked from commit 0a505ca83d
2020-11-30 11:43:03 -08:00
Sven Mika
bb03e2499b
[RLlib] PyBullet Env native support via env str-specifier (if installed). ( #12209 )
2020-11-30 12:41:24 +01:00
Sven Mika
fb318addcb
[RLlib] Curiosity exploration module: tf/tf2.x/tf-eager support. ( #11945 )
2020-11-29 12:31:24 +01:00
Pierre TASSEL
60a545ab57
[RLLib] Fix HyperOptSearch tuple to list conversion ( #12462 )
...
Co-authored-by: Sumanth Ratna <sumanthratna@gmail.com>
2020-11-28 10:07:54 -08:00
Sven Mika
0df55a139c
[RLlib] Attention Net prep PR #1 : Smaller cleanups. ( #12447 )
...
* WIP.
* Fix.
* Fix.
* Fix.
2020-11-27 16:25:47 -08:00
Sven Mika
6475297bd3
[RLlib] Torch LR schedule not working. Fix and added test case. ( #12396 )
2020-11-26 13:14:11 +01:00
Sven Mika
b7dbbfbf41
[RLlib] Issue 11591: SAC loss does not use PR-weights in critic loss term. ( #12394 )
...
* WIP.
* Fix and LINT.
2020-11-25 11:28:46 -08:00
Sven Mika
592c161032
[RLlib] Issue 12118: LSTM prev-a/r should be separately configurable. Fix missing prev-a one-hot encoding. ( #12397 )
...
* WIP.
* Fix and LINT.
2020-11-25 11:27:46 -08:00
Sven Mika
841d93d366
[RLlib] Issue 12233 shared tf layers example not really shared (only works for tf1.x, not tf2.x). ( #12399 )
2020-11-25 11:27:19 -08:00
Sven Mika
95175a822f
[RLlib] Issue 11974: Traj view API next-action (shift=+1) not working. ( #12407 )
...
* WIP.
* Fix and LINT.
2020-11-25 11:26:29 -08:00
karstenddwx
09d5413f70
[RLlib] rollout batch, handle rewards that are None (unknown) in a multi-agent env ( #11858 ) ( #11911 )
2020-11-25 13:39:22 +01:00
danuo
c009c178f6
[RLlib] Closes #11924 : Add support for custom/ray environments in rollouts.py for agents without workers ( #11926 )
...
* Closes #11924
Formerly, rollout.py would only load environments from gym (with
gym.make() ) , if an agent without workers is employed (such as ES or
ARS). This will result in an error, if a custom environment is used. This
PR adds the possibility to load environments from the ray registry,
while maintaining the support for gym environments.
* Update rllib/rollout.py
Co-authored-by: Sven Mika <sven@anyscale.io>
2020-11-25 08:43:17 +01:00
Tomasz Wrona
82852f0ed2
[RLlib] Add ResetOnExceptionWrapper with tests for unstable 3rd party envs ( #12353 )
2020-11-25 08:41:58 +01:00
Sven Mika
4afaa46028
[RLlib] Increase the scope of RLlib's regression tests. ( #12200 )
2020-11-24 22:18:31 +01:00
Edward Oakes
32d159a2ed
Fix release directory & RELEASE_PROCESS.md ( #12269 )
2020-11-23 14:28:59 -06:00
Sven Mika
f6b84cb2f7
[RLlib] Fix offline logp vs prob bug in OffPolicyEstimator class. ( #12158 )
2020-11-20 08:59:43 +01:00
Raoul Khouri
d07ffc152b
[rllib] Rrk/12079 custom filters ( #12095 )
...
* travis reformatted
2020-11-19 13:20:20 -08:00
Sven Mika
dab241dcc6
[RLlib] Fix inconsistency wrt batch size in SampleCollector (traj. view API). Makes DD-PPO work with traj. view API. ( #12063 )
2020-11-19 19:01:14 +01:00
Sven Mika
6da4342822
[RLlib] Add on_learn_on_batch (Policy) callback to DefaultCallbacks. ( #12070 )
2020-11-18 15:39:23 +01:00
Sven Mika
b6b54f1c81
[RLlib] Trajectory view API: enable by default for SAC, DDPG, DQN, SimpleQ ( #11827 )
2020-11-16 10:54:35 -08:00
