Simon Mo
9f23affdc0
[Hotfix] Unbreak lint in master ( #24794 )
2022-05-13 15:05:05 -07:00
kourosh hakhamaneshi
ffcbb30552
[RLlib] Move from agents to algorithms - CQL, MARWIL, AlphaStar, MAML, Dreamer, MBMPO. ( #24739 )
2022-05-13 18:43:36 +02:00
Sven Mika
f54557073e
[RLlib] Remove execution_plan API code no longer needed. ( #24501 )
2022-05-06 12:29:53 +02:00
Sven Mika
1bc6419e0e
[RLlib] R2D2 training iteration fn AND switch off execution_plan API by default. ( #24165 )
2022-05-03 07:59:26 +02:00
Sven Mika
a3d4fc74a6
[RLlib] MARWIL: Move to training_iteration API. ( #23798 )
2022-04-11 19:28:32 +02:00
Balaji Veeramani
31ed9e5d02
[CI] Replace YAPF disables with Black disables ( #21982 )
2022-02-08 16:29:25 -08:00
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
Jun Gong
55f3bcfb2d
[RLlib] Add a logstd term to MARWIL's loss func to encourage exploration. ( #21493 )
2022-01-26 16:00:17 +01:00
Sven Mika
b10d5533be
[RLlib] Issue 20920 (partial solution): contrib/MADDPG + pettingzoo coop-pong-v4 not working. ( #21452 )
2022-01-10 11:19:40 +01:00
Sven Mika
b4790900f5
[RLlib] Sub-class Trainer (instead of build_trainer()): All remaining classes; soft-deprecate build_trainer. ( #20725 )
2021-12-04 22:05:26 +01:00
Sven Mika
60b2219d72
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. ( #20757 )
2021-12-04 13:26:33 +01:00
Artur Niederfahrenhorst
d07e50e957
[RLlib] Replay buffer API (cleanups; docstrings; renames; move into rllib/execution/buffers dir) ( #20552 )
2021-11-19 11:57:37 +01:00
Sven Mika
f82880eda1
Revert "Revert [RLlib] POC: Deprecate build_policy (policy template) for torch only; PPOTorchPolicy ( #20061 ) ( #20399 )" ( #20417 )
...
This reverts commit 90dc5460d4
2021-11-16 14:49:41 +01:00
Amog Kamsetty
90dc5460d4
Revert "[RLlib] POC: Deprecate build_policy (policy template) for torch only; PPOTorchPolicy ( #20061 )" ( #20399 )
...
This reverts commit 5b1c8e46e1
2021-11-15 16:11:35 -08:00
Sven Mika
5b1c8e46e1
[RLlib] POC: Deprecate build_policy (policy template) for torch only; PPOTorchPolicy ( #20061 )
2021-11-15 10:41:54 +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
Sven Mika
cf21c634a3
[RLlib] Fix deprecated warning for torch_ops.py (soft-replaced by torch_utils.py). ( #19982 )
2021-11-03 10:00:46 +01:00
Sven Mika
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils ( #19829 )
2021-11-01 21:46:02 +01:00
Sven Mika
9c73871da0
[RLlib; Docs overhaul] Docstring cleanup: Evaluation ( #19783 )
2021-10-29 12:03:56 +02:00
gjoliver
99a0088233
[RLlib] Unify the way we create local replay buffer for all agents ( #19627 )
...
* [RLlib] Unify the way we create and use LocalReplayBuffer for all the agents.
This change
1. Get rid of the try...except clause when we call execution_plan(),
and get rid of the Deprecation warning as a result.
2. Fix the execution_plan() call in Trainer._try_recover() too.
3. Most importantly, makes it much easier to create and use different types
of local replay buffers for all our agents.
E.g., allow us to easily create a reservoir sampling replay buffer for
APPO agent for Riot in the near future.
* Introduce explicit configuration for replay buffer types.
* Fix is_training key error.
* actually deprecate buffer_size field.
2021-10-26 20:56:02 +02:00
Sven Mika
b213565783
[RLlib] Fix failing test cases: Soft-deprecate ModelV2.from_batch (in favor of ModelV2.__call__). ( #19693 )
2021-10-25 15:00:00 +02:00
gjoliver
89fbfc00f8
[RLlib] Some minor cleanups (buffer buffer_size -> capacity and others). ( #19623 )
2021-10-25 09:42:39 +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
Sven Mika
e2be41b407
[RLlib] MARWIL + BC: Various fixes and enhancements. ( #16218 )
2021-06-03 22:29:00 +02:00
Sven Mika
f6302d81be
[RLlib] Discussion 2210: BC algo broken, if "advantages" missing in offline data. ( #16019 )
2021-05-25 08:47:17 +02:00
Sven Mika
eaa7f6696d
[RLlib] Issue 15887: MARWIL adv norm update mismatch for tf (static-graph) vs torch versions. ( #15898 )
2021-05-19 15:44:11 -07:00
Michael Luo
474f04e322
[RLlib] DDPG/TD3 + A3C/A2C + MARWIL/BC Annotation/Comments/Code Cleanup ( #14707 )
2021-05-19 16:32:29 +02:00
Sven Mika
839fc59224
[RLlib] CQL TensorFlow support ( #15841 )
2021-05-18 11:10:46 +02:00
Sven Mika
c4a3e1589b
[RLlib] CQL: Bug fixes and OPE example added to test and offline_rl.py example. ( #15761 )
2021-05-13 09:17:23 +02:00
Michael Luo
4cbe13cdfd
[RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. ( #15603 )
...
Co-authored-by: Sven Mika <sven@anyscale.io>
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-05-04 19:06:19 +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
8b3554e37e
[RLlib] Remove all (already soft-deprecated) SampleBatch.data from code. ( #15335 )
2021-04-15 19:19:51 +02:00
Sven Mika
1bb70e4907
[RLlib] Issue 14523: Torch + py3.8 leads to GPU device error. ( #15014 )
2021-03-30 21:43:11 +02:00
Sven Mika
6708211b59
[RLlib] JSONReader: Mix files if > 1 at beginning (each worker should start with different file). ( #14865 )
2021-03-24 16:07:40 +01:00
Sven Mika
04bc0a9828
[RLlib] Remove all non-trajectory view API code. ( #14860 )
2021-03-23 09:50:18 -07:00
Sven Mika
69202c6a7d
[RLlib] Obsolete usage tracking dict via sample batch. ( #13065 )
2021-03-17 08:18:15 +01:00
Sven Mika
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. ( #13393 )
2021-03-08 15:41:27 +01:00
Sven Mika
eb0038612f
[RLlib] Extend on_learn_on_batch callback to allow for custom metrics to be added. ( #13584 )
2021-02-08 15:02:19 +01:00
Sven Mika
d629292d63
[RLlib] Add grad_clip config option to MARWIL and stabilize grad clipping against inf global_norms. ( #13634 )
2021-01-22 19:36:02 +01:00
Sven Mika
a65ee92b69
[RLlib] MARWIL loss function test case and cleanup. ( #13455 )
2021-01-19 09:51:05 +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
99ae7bae05
[RLlib] JAXPolicy prep. PR #1 . ( #13077 )
2020-12-26 20:14:18 -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
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
ce96b03b07
[RLlib] MB-MPO cleanup (comments, docstrings, type annotations). ( #11033 )
2020-10-06 20:28:16 +02:00
Eric Liang
ecdaaffc67
add large data warning ( #10957 )
2020-09-23 15:46:06 -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
Sven Mika
4b278c36fc
[RLlib] Behavioral Cloning (from MARWIL). ( #10619 )
2020-09-09 17:33:21 +02:00
Barak Michener
8e76796fd0
ci: Redo format.sh --all script & backfill lint fixes ( #9956 )
2020-08-07 16:49:49 -07:00
