Commit graph

267 commits

Author SHA1 Message Date
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
ea25482f6a
WIP. (#12706) 2020-12-09 11:49:21 -08:00
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
Sven Mika
99c81c6795
[RLlib] Attention Net prep PR #3. (#12450) 2020-12-07 13:08:17 +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
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
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
Michael Luo
59bc1e6c09
[RLLib] MAML extension for all models except RNNs (#11337) 2020-11-12 16:51:40 -08:00
Sven Mika
0bd69edd71
[RLlib] Trajectory view API: enable by default for ES and ARS (#11826) 2020-11-12 10:33:10 -08:00
Michael Luo
6e6c680f14
MBMPO Cartpole (#11832)
* MBMPO Cartpole Done

* Added doc
2020-11-12 10:30:41 -08:00
Sven Mika
62c7ab5182
[RLlib] Trajectory view API: Enable by default for PPO, IMPALA, PG, A3C (tf and torch). (#11747) 2020-11-12 16:27:34 +01:00
Sven Mika
291c172d83
[RLlib] Support Simplex action spaces for SAC (torch and tf). (#11909) 2020-11-11 18:45:28 +01:00
Eric Liang
9b8218aabd
[docs] Move all /latest links to /master (#11897)
* use master link

* remae

* revert non-ray

* more

* mre
2020-11-10 10:53:28 -08:00
Eric Liang
6b7a4dfaa0
[rllib] Forgot to pass ioctx to child json readers (#11839)
* fix ioctx

* fix
2020-11-05 22:07:57 -08:00
Sven Mika
d6c7c7c675
[RLlib] Make sure, DQN torch actions are of type=long before torch.nn.functional.one_hot() op. (#11800) 2020-11-04 18:04:03 +01:00
desktable
5af745c90d
[RLlib] Implement the SlateQ algorithm (#11450) 2020-11-03 09:52:04 +01:00
Sven Mika
bfc4f95e01
[RLlib] Fix test_bc.py test case. (#11722)
* Fix large json test file.

* Fix large json test file.

* WIP.
2020-10-31 00:16:09 -07:00
Sven Mika
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609) 2020-10-27 10:00:24 +01:00
Kingsley Kuan
d1dd5d578e
[RLlib] Fix PyTorch A3C / A2C loss function using mixed reduced sum / mean (#11449) 2020-10-22 12:39:34 -07:00
Philsik Chang
ede9347127
[rllib] Add torch_distributed_backend flag for DDPPO (#11362) (#11425) 2020-10-21 18:30:42 -07:00
Eric Liang
e8c77e2847
Remove memory quota enforcement from actors (#11480)
* wip

* fix

* deprecate
2020-10-21 14:29:03 -07:00
Sven Mika
414041c6dd
[RLlib] Do not create env on driver iff num_workers > 0. (#11307) 2020-10-15 18:21:30 +02:00
Sven Mika
0c0f67c14d
[RLlib] ARS/ES eval workers not working: Issue 9933. (#11308) 2020-10-12 13:49:48 -07:00
Sven Mika
f5e2cda68a
[RLlib] SAC: log_alpha not being learnt when on GPU. (#11298) 2020-10-12 13:48:44 -07:00
Julius Frost
7dcfd258cd
[RLlib] Assert LongTensor in SAC Discrete PyTorch (#11245) 2020-10-12 13:47:21 -07:00
Sven Mika
d3bc20b727
[RLlib] ConvTranspose2D module (#11231) 2020-10-12 15:00:42 +02:00
Sumanth Ratna
14d8826e43
Fix overriden typo (#11227) 2020-10-07 19:11:07 -07:00
Sven Mika
ce96b03b07
[RLlib] MB-MPO cleanup (comments, docstrings, type annotations). (#11033) 2020-10-06 20:28:16 +02:00
Sven Mika
c17169dc11
[RLlib] Fix all example scripts to run on GPUs. (#11105) 2020-10-02 23:07:44 +02:00
Michael Luo
47b499d899
Cartpole MAML + Discrete (#11028) 2020-10-02 12:56:34 +02:00
Sven Mika
36bda8432b
[RLlib] Trajectory view API: Simple List Collector (on by default for PPO); LSTM-agnostic (#11056) 2020-10-01 16:57:10 +02:00
Eric Liang
ecdaaffc67
add large data warning (#10957) 2020-09-23 15:46:06 -07:00
Michael Luo
ba5a3ae9e2
Enable vtrace by default (#10962) 2020-09-22 22:18:21 -07:00
mvindiola1
2b893d1bb5
fix incorrect critic loss in TD3 (#10775)
Co-authored-by: Manny Vindiola <manuel.m.vindiola.civ@mail.mil>
2020-09-20 20:01:51 -07:00
Sven Mika
805dad3bc4
[RLlib] SAC algo cleanup. (#10825) 2020-09-20 11:27:02 +02:00
Sumanth Ratna
9da7bdcc8e
Use master for links to docs in source (#10866) 2020-09-19 00:30:45 -07:00
Eric Liang
f83c588f08
[rllib] Remove broken no eager on workers mode (#10745)
* remove no eager

* Update trainer.py
2020-09-15 17:25:20 -07:00
desktable
4ccfd07a61
[RLlib] Add docstrings for agents/dqn (#10710) 2020-09-15 12:37:07 +02:00
maxco2
b8436f0f00
[rllib] Fix SAC and DDPG tensorflow policy can't do grad_clip (#10499)
* Fix sac_tf_policy clip_by_norm missing argument

* Fix ddpg_tf_policy clip_by_norm missing argument

* Fix format
2020-09-11 12:04:44 -07:00
Julius Frost
e72838c03d
[RLLib] Add missing .to() for MARWIL on PyTorch (#10685)
There was a missing .to() that caused a device mismatch error on PyTorch with MARWIL.
2020-09-09 18:52:55 -07:00
desktable
799318d7d7
[RLlib] Add type annotations for agents/dqn (#10626) 2020-09-09 18:55:26 +02:00
Sven Mika
4b278c36fc
[RLlib] Behavioral Cloning (from MARWIL). (#10619) 2020-09-09 17:33:21 +02:00