gjoliver
89fbfc00f8
[RLlib] Some minor cleanups (buffer buffer_size -> capacity and others). ( #19623 )
2021-10-25 09:42:39 +02:00
gjoliver
44a4e42172
[rllib] Add entropy_coeff_schedule support for APPO. ( #19544 )
...
* Add entropy_coeff_schedule support for APPO.
* lint
2021-10-20 14:18:01 -07:00
Sven Mika
bd2d2079d2
[RLlib] Support >1 loss terms and optimizers for framework=tf2 (already supported for framework=[tf|torch]) ( #19269 )
2021-10-10 12:19:47 +02:00
Sven Mika
d439fd7f17
[RLlib] TF2/eager memory leak fixes. ( #19198 )
2021-10-09 00:11:53 +02:00
Sven Mika
b4300dd532
[RLlib] Issue 18812: Torch multi-GPU stats not protected against race conditions. ( #18937 )
2021-10-04 13:29:00 +02:00
Sven Mika
ed85f59194
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. ( #18879 )
2021-09-30 16:39:05 +02:00
Avnish Narayan
6dc1a6b72f
[RLlib] Raise error for kl penalty ddpo ( #18959 )
...
* [RLlib] Raise error for kl penalty ddpo
DDPPO doesn't support KL penalties like PPO-1.
In order to support KL penalties, DDPPO would need to
become undecentralized, which defeats the purpose of the
algorithm. Users can still tune the entropy coefficient to
control the policy entropy (similar to controlling the KL
penalty.)
* Update rllib/agents/ppo/ddppo.py
Co-authored-by: avnishn <avnishnarayan@gmail.com>
Co-authored-by: Sven Mika <sven@anyscale.io>
2021-09-30 10:56:22 +02:00
Sven Mika
698b4eeed3
[RLlib] POC: Separate losses for APPO/IMPALA. Enable TFPolicy to handle multiple optimizers/losses (like TorchPolicy). ( #18669 )
2021-09-21 22:00:14 +02:00
Sven Mika
45f60e51a9
[RLlib] DDPPO fixes and benchmarks. ( #18390 )
2021-09-08 19:39:01 +02:00
Sven Mika
599e589481
[RLlib] Move existing fake multi-GPU learning tests into separate buildkite job. ( #18065 )
2021-08-31 14:56:53 +02:00
Sven Mika
a428f10ebe
[RLlib] Add multi-GPU learning tests to nightly. ( #17778 )
2021-08-18 17:21:01 +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
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
649580d735
[RLlib] Redo simplify multi agent config dict: Reverted b/c seemed to break test_typing (non RLlib test). ( #17046 )
2021-07-15 05:51:24 -04:00
Amog Kamsetty
38b5b6d24c
Revert "[RLlib] Simplify multiagent config (automatically infer class/spaces/config). ( #16565 )" ( #17036 )
...
This reverts commit e4123fff27
2021-07-13 09:57:15 -07:00
Sven Mika
e4123fff27
[RLlib] Simplify multiagent config (automatically infer class/spaces/config). ( #16565 )
2021-07-13 06:38:14 -04:00
Sven Mika
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes ( #16531 )
2021-06-30 12:32:11 +02:00
Sven Mika
e80095591c
[RLlib] Entropy coeff schedule bug fix and git bisect script. ( #15937 )
2021-05-20 18:15:10 +02:00
Sven Mika
2303851c3c
[RLlib] Torch multi-GPU + LSTM/RNN bug fix. ( #15492 )
2021-05-18 11:51:05 +02:00
Sven Mika
461d73ddf1
[RLlib] simple_optimizer should not be used by default for tf+MA. ( #15365 )
2021-05-10 16:10:44 +02:00
Sven Mika
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. ( #15273 )
2021-04-30 19:26:30 +02:00
Sven Mika
bb8a286cbc
[RLlib] Support native tf.keras.Model (milestone toward obsoleting ModelV2 class). ( #14684 )
2021-04-27 10:44:54 +02:00
Sven Mika
cecfc3b43b
[RLlib] Multi-GPU support for Torch algorithms. ( #14709 )
2021-04-16 09:16:24 +02:00
Sven Mika
4f66309e19
[RLlib] Redo issue 14533 tf enable eager exec ( #14984 )
2021-03-29 20:07:44 +02:00
SangBin Cho
fa5f961d5e
Revert "[RLlib] Issue 14533: tf.enable_eager_execution() must be called at beginning. ( #14737 )" ( #14918 )
...
This reverts commit 3e389d5812
2021-03-25 00:42:01 -07:00
Sven Mika
3e389d5812
[RLlib] Issue 14533: tf.enable_eager_execution() must be called at beginning. ( #14737 )
2021-03-24 12:54:27 +01:00
Sven Mika
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. ( #13393 )
2021-03-08 15:41:27 +01:00
Sven Mika
775e685531
[RLlib] Issue #13824 : compress_observations=True crashes for all algos not using a replay buffer. ( #14034 )
2021-02-18 21:36:32 +01:00
Sven Mika
2e3655e8a9
[RLlib] Issue 9071 A3C w/ RNN not working due to VF assuming no RNN. ( #13238 )
2021-01-19 14:22:36 +01:00
Sven Mika
93c0a5549b
[RLlib] Deprecate vf_share_layers in top-level PPO/MAML/MB-MPO configs. ( #13397 )
2021-01-19 09:51:35 +01:00
Sven Mika
c524f86785
[RLlib] BC/MARWIL/recurrent nets minor cleanups and bug fixes. ( #13064 )
2020-12-27 09:46:03 -05:00
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
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
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
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
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). ( #11609 )
2020-10-27 10:00:24 +01:00
Sven Mika
c17169dc11
[RLlib] Fix all example scripts to run on GPUs. ( #11105 )
2020-10-02 23:07:44 +02:00
Sven Mika
ef18893fb5
[RLlib] PPO, APPO, and DD-PPO code cleanup. ( #10420 )
2020-09-02 14:03:01 +02:00
Chua Cheow Huan
ea51e94729
[rllib] Learning rate schedule for DDPPO. ( #10006 )
...
* Get shared metrics, increment counter & set global vars for remote workers.
* Add unit test to test lr_schedule for DDPPO.
* Broadcast the local set of global vars to remote workers instead of independently setting the global vars on each rollout worker.
2020-08-15 00:51:45 -07:00
Barak Michener
8e76796fd0
ci: Redo format.sh --all script & backfill lint fixes ( #9956 )
2020-08-07 16:49:49 -07:00
Sven Mika
fcdf410ae1
[RLlib] Tf2.x native. ( #8752 )
2020-07-11 22:06:35 +02:00
Sven Mika
43043ee4d5
[RLlib] Tf2x preparation; part 2 (upgrading try_import_tf()). ( #9136 )
...
* WIP.
* Fixes.
* LINT.
* WIP.
* WIP.
* Fixes.
* Fixes.
* Fixes.
* Fixes.
* WIP.
* Fixes.
* Test
* Fix.
* Fixes and LINT.
* Fixes and LINT.
* LINT.
2020-06-30 10:13:20 +02:00
Sven Mika
5c6d5d4ab1
This PR fixes the currently broken lstm_use_prev_action_reward flag for default lstm models (model.use_lstm=True). ( #8970 )
2020-06-27 20:50:01 +02:00
Sven Mika
7008902cff
[RLlib] Minor rllib.utils cleanup. ( #8932 )
2020-06-16 08:52:20 +02:00
Sven Mika
4ed796a7d6
[RLlib] Add testing Policy.compute_single_action() for all agents. ( #8903 )
2020-06-13 17:51:50 +02:00
Sven Mika
2746fc0476
[RLlib] Auto-framework, retire use_pytorch in favor of framework=... ( #8520 )
2020-05-27 16:19:13 +02:00
Eric Liang
7ce138a6dc
[rllib] Support free_log_std in ModelV2 ( #8380 )
...
* update
* factor
* update
* fix test failures
* fix torch net
2020-05-12 10:14:05 -07:00
Eric Liang
9d012626e5
[rllib] Distributed exec workflow for impala ( #8321 )
2020-05-11 20:24:43 -07:00
Sven Mika
754290daad
[RLlib] Add light-weight Trainer.compute_action() tests for all Algos. ( #8356 )
2020-05-08 16:31:31 +02:00
