Artur Niederfahrenhorst
d76ef9add5
[RLLib] Fix RNNSAC example failing on CI + fixes for recurrent models for other Q Learning Algos. ( #24923 )
2022-05-24 14:39:43 +02:00
Sven Mika
ec89fe5203
[RLlib] APEX-DQN and R2D2 config objects. ( #25067 )
2022-05-23 12:15:45 +02:00
kourosh hakhamaneshi
3815e52a61
[RLlib] Agents to algos: DQN w/o Apex and R2D2, DDPG/TD3, SAC, SlateQ, QMIX, PG, Bandits ( #24896 )
2022-05-19 18:30:42 +02:00
Artur Niederfahrenhorst
fb2915d26a
[RLlib] Replay Buffer API and Ape-X. ( #24506 )
2022-05-17 13:43:49 +02:00
Sven Mika
25001f6d8d
[RLlib] APPO Training iteration fn. ( #24545 )
2022-05-17 10:31:07 +02:00
Steven Morad
5c96e7223b
[RLlib] SimpleQ (minor cleanups) and DQN TrainerConfig objects. ( #24584 )
2022-05-15 16:14:43 +02:00
Max Pumperla
6a6c58b5b4
[RLlib] Config objects for DDPG and SimpleQ. ( #24339 )
2022-05-12 16:12:42 +02:00
Artur Niederfahrenhorst
95d4a83a87
[RLlib] R2D2 Replay Buffer API integration. ( #24473 )
2022-05-10 20:36:14 +02:00
Sven Mika
f066180ed5
[RLlib] Deprecate timesteps_per_iteration config key (in favor of min_[sample|train]_timesteps_per_reporting. ( #24372 )
2022-05-02 12:51:14 +02:00
Avnish Narayan
477b9d22d2
[RLlib][Training iteration fn] APEX conversion ( #22937 )
2022-04-20 17:56:18 +02:00
Artur Niederfahrenhorst
e57ce7efd6
[RLlib] Replay Buffer API and Training Iteration Fn for DQN. ( #23420 )
2022-04-18 12:20:12 +02:00
Balaji Veeramani
7f1bacc7dc
[CI] Format Python code with Black ( #21975 )
...
See #21316 and #21311 for the motivation behind these changes.
2022-01-29 18:41:57 -08:00
Sven Mika
d5bfb7b7da
[RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 ( #21652 )
2022-01-25 14:16:58 +01:00
Sven Mika
a931076f59
[RLlib] Tf2 + eager-tracing same speed as framework=tf; Add more test coverage for tf2+tracing. ( #19981 )
2021-11-05 16:10:00 +01:00
Avnish Narayan
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. ( #19535 )
...
* Fix QMix, SAC, and MADDPA too.
* Unpin gym and deprecate pendulum v0
Many tests in rllib depended on pendulum v0,
however in gym 0.21, pendulum v0 was deprecated
in favor of pendulum v1. This may change reward
thresholds, so will have to potentially rerun
all of the pendulum v1 benchmarks, or use another
environment in favor. The same applies to frozen
lake v0 and frozen lake v1
Lastly, all of the RLlib tests and have
been moved to python 3.7
* Add gym installation based on python version.
Pin python<= 3.6 to gym 0.19 due to install
issues with atari roms in gym 0.20
* Reformatting
* Fixing tests
* Move atari-py install conditional to req.txt
* migrate to new ale install method
* Fix QMix, SAC, and MADDPA too.
* Unpin gym and deprecate pendulum v0
Many tests in rllib depended on pendulum v0,
however in gym 0.21, pendulum v0 was deprecated
in favor of pendulum v1. This may change reward
thresholds, so will have to potentially rerun
all of the pendulum v1 benchmarks, or use another
environment in favor. The same applies to frozen
lake v0 and frozen lake v1
Lastly, all of the RLlib tests and have
been moved to python 3.7
* Add gym installation based on python version.
Pin python<= 3.6 to gym 0.19 due to install
issues with atari roms in gym 0.20
Move atari-py install conditional to req.txt
migrate to new ale install method
Make parametric_actions_cartpole return float32 actions/obs
Adding type conversions if obs/actions don't match space
Add utils to make elements match gym space dtypes
Co-authored-by: Jun Gong <jungong@anyscale.com>
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-11-03 16:24:00 +01:00
gjoliver
9385b6c1be
[RLlib] Make a few LRSchedule and EntropyCoeffSchedule tests more reliable. ( #19934 )
2021-11-02 16:52:56 +01:00
Sven Mika
2d24ef0d32
[RLlib] Add all simple learning tests as framework=tf2. ( #19273 )
...
* Unpin gym and deprecate pendulum v0
Many tests in rllib depended on pendulum v0,
however in gym 0.21, pendulum v0 was deprecated
in favor of pendulum v1. This may change reward
thresholds, so will have to potentially rerun
all of the pendulum v1 benchmarks, or use another
environment in favor. The same applies to frozen
lake v0 and frozen lake v1
Lastly, all of the RLlib tests and Tune tests have
been moved to python 3.7
* fix tune test_sampler::testSampleBoundsAx
* fix re-install ray for py3.7 tests
Co-authored-by: avnishn <avnishn@uw.edu>
2021-11-02 12:10:17 +01:00
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
Sven Mika
8a00154038
[RLlib] Bump tf version in ML docker to tf==2.5.0; add tfp to ML-docker. ( #18544 )
2021-09-15 08:46:37 +02:00
gjoliver
808b683f81
[RLlib] Add a unittest for learning rate schedule used with APEX agent. ( #18389 )
2021-09-08 23:29:40 +02:00
Sven Mika
e3e6ed7aaa
[RLlib] Issues 17844, 18034: Fix n-step > 1 bug. ( #18358 )
2021-09-06 12:14:20 +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
4888d7c9af
[RLlib] Replay buffers: Add config option to store contents in checkpoints. ( #17999 )
2021-08-31 12:21:49 +02:00
Sven Mika
a428f10ebe
[RLlib] Add multi-GPU learning tests to nightly. ( #17778 )
2021-08-18 17:21:01 +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
8a844ff840
[RLlib] Issues: 17397, 17425, 16715, 17174. When on driver, Torch|TFPolicy should not use ray.get_gpu_ids() (b/c no GPUs assigned by ray). ( #17444 )
2021-08-02 17:29:59 -04:00
Sven Mika
5a313ba3d6
[RLlib] Refactor: All tf static graph code should reside inside Policy class. ( #17169 )
2021-07-20 14:58:13 -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
d0014cd351
[RLlib] Policies get/set_state fixes and enhancements. ( #16354 )
2021-06-15 13:08:43 +02:00
Sven Mika
2d34216660
[RLlib] APEX-DQN: Bug fix for torch and add learning test. ( #15762 )
2021-05-20 09:27:03 +02:00
Sven Mika
16ddab49f5
[RLlib] Trainer._evaluate -> Trainer.evaluate; Also make evaluation possible w/o evaluation worker set. ( #15591 )
2021-05-12 12:16:00 +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
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. ( #13393 )
2021-03-08 15:41:27 +01:00
Sven Mika
8000258333
[RLlib] R2D2 Implementation. ( #13933 )
2021-02-25 12:18:11 +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
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
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
5dc4b6686e
[RLlib] Implement DQN PyTorch distributional head. ( #9589 )
2020-07-25 09:29:24 +02:00
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
4ed796a7d6
[RLlib] Add testing Policy.compute_single_action() for all agents. ( #8903 )
2020-06-13 17:51:50 +02:00
Eric Liang
34bae27ac7
[rllib] Flexible multi-agent replay modes and replay_sequence_length ( #8893 )
2020-06-12 20:17:27 -07:00
Sven Mika
d8a081a185
[RLlib] Unity3D integration (n Unity3D clients vs learning server). ( #8590 )
2020-05-30 22:48:34 +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
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
Sven Mika
b95e28faea
[RLlib] APEX_DDPG (PyTorch) test case and docs. ( #8288 )
...
APEX_DDPG (PyTorch) test case and docs.
2020-05-04 09:36:27 +02:00
Eric Liang
2298f6fb40
[rllib] Port DQN/Ape-X to training workflow api ( #8077 )
2020-04-23 12:39:19 -07:00
Sven Mika
d6cb7d865e
[RLlib] Torch DQN (APEX) TD-Error/prio. replay fixes. ( #8082 )
...
PyTorch APEX_DQN with Prioritized Replay enabled would not work properly due to the td_error not being retrievable by the AsyncReplayOptimizer.
2020-04-20 10:03:25 +02:00
