gjoliver
d81885c1f1
[RLlib] Fix all the CI tests that were broken by is_training and replay buffer changes; re-comment-in the failing RLlib tests ( #19809 )
...
* Fix DDPG, since it is based on GenericOffPolicyTrainer.
* Fix QMix, SAC, and MADDPA too.
* Undo QMix change.
* Fix DQN input batch type. Always use SampleBatch.
* apex ddpg should not use replay_buffer_config yet.
* Make eager tf policy to use SampleBatch.
* lint
* LINT.
* Re-enable RLlib broken tests to make sure things work ok now.
* fixes.
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-10-28 18:06:47 +02:00
Simon Mo
5e927b01ad
Revert "[CI] Remove config that disables Bazel test result cache" ( #19818 )
...
* Revert "[CI] Remove config that disables Bazel test result cache (#18701 )"
This reverts commit 098ff36faa
2021-10-28 15:54:53 +02:00
gjoliver
39b0faa3ec
[RLlib]: bug fix, should be input_dict['is_training'] ( #19805 )
2021-10-27 23:30:43 +02:00
Sven Mika
4a82d3ea6c
Revert "[RLlib; Docs overhaul] Docstring cleanup: Trainer, trainer_template, Callbacks. ( #19758 )" ( #19806 )
...
This reverts commit 80eeb13175
2021-10-27 23:30:07 +02:00
Sven Mika
80eeb13175
[RLlib; Docs overhaul] Docstring cleanup: Trainer, trainer_template, Callbacks. ( #19758 )
2021-10-27 19:15:35 +02:00
Sven Mika
f2cb2ed203
[RLlib; Docs overhaul] Docstring cleanup: Policies, policy_templates. ( #19759 )
2021-10-27 19:14:39 +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
Avnish Narayan
ad87ddf93e
[rllib] Add deterministic test to gpu ( #19306 )
...
Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-10-26 10:11:39 -07:00
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
roireshef
9b0352f363
[RLlib] Added LearningRateSchedule and EntropyCoeffSchedule to TF and Torch versions of A3C and PPO ( #19276 )
2021-10-25 09:39:35 +02:00
gjoliver
c3c42278e4
[RLlib] clean up all the SampleBatch['is_training'] deprecation warnings ( #19652 )
...
* [RLlib] clean up all the SampleBatch['is_training'] deprecation warnings.
* wip
2021-10-25 09:38:56 +02:00
xwjiang2010
a632cb439f
[Tune] Remove queue_trials. ( #19472 )
2021-10-22 09:24:54 +01:00
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
Carlo Grisetti
5cee8a1985
[release tests] Switch from yaml.load to yaml.safe_load ( #19365 )
2021-10-13 17:27:25 -07:00
Antoine Galataud
edb338ff7c
[RLlib] Check training_enabled on PolicyServer ( #19007 )
2021-10-12 16:21:02 +02:00
gjoliver
9226f9bddc
[RLlib] Report timesteps_this_iter to Tune, so it can track/checkpoint/restore total timesteps trained. ( #19264 )
...
* Report timesteps_this_iter to Tune, so it can track/checkpoint/restore
total timesteps trained.
* Trigger Build
* lint
2021-10-12 16:03:41 +02:00
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
c3e3fc7637
[RLlib] Issue 18280: A3C/IMPALA multi-agent not working. ( #19100 )
2021-10-07 23:57:53 +02:00
Sven Mika
fd438d5630
[RLlib] Issue 18104: Cannot set remote_worker_envs=True for non local-mode and MultiAgentEnv. ( #19133 )
2021-10-07 22:39:21 +02:00
Sven Mika
1f0646f658
[RLlib] Issue 18418: SAC w/ dict space not working. ( #19101 )
2021-10-06 09:05:50 +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
73f5c4039b
[RLlib] Fix flakey test_a3c, test_maml, test_apex_dqn. ( #19035 )
2021-10-04 13:23:51 +02:00
Jiajun Yao
7588bfd315
[Lint] Add flake8-bugbear ( #19053 )
...
* Add flake8-bugbear
* Add flake8-bugbear
2021-10-03 23:24:11 -07:00
Sven Mika
16ad46a654
[RLlib] Fix broken test_r2d2.py. ( #19017 )
2021-09-30 21:19:37 +02:00
Sven Mika
ac3371a148
[RLlib] Discussion 3644: Fix bug for complex obs spaces containing Box([2D shape]) and discrete component. ( #18917 )
2021-09-30 16:39:38 +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
828f5d26b7
[RLlib] Custom view requirements (e.g. for prev-n-obs) work with compute_single_action and compute_actions_from_input_dict. ( #18921 )
2021-09-30 15:03:37 +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
05a55a9335
[RLlib] Issue 18668: Unity3D env client/server example not working (fix + add to test cases). ( #18942 )
2021-09-30 08:30:20 +02:00
Sven Mika
9c9b482661
[RLlib] Allow n-step > 1 and prio. replay for R2D2 and RNNSAC. ( #18939 )
2021-09-29 21:31:34 +02:00
Sven Mika
b99943806e
[RLlib] Add support for IMPALA to handle more than one loss/optimizer (analogous to recent enhancement for APPO). ( #18971 )
2021-09-29 21:30:04 +02:00
mvindiola1
62f5da0b65
[RLlib] Add unit tests for updating episode data in base_env ( #17137 )
2021-09-24 16:08:11 +02:00
Julius Frost
8b8b447fd7
[RLlib] Fix train.py input config patching ( #18747 )
2021-09-24 14:41:33 +02:00
o0olele
ff6730f903
[RLlib] Attention Nets + MultiDiscrete spaces: Fix range() takes no keyword args error! ( #17502 )
2021-09-24 13:43:58 +02:00
Sven Mika
61a1274619
[RLlib] No Preprocessors (part 2). ( #18468 )
2021-09-23 12:56:45 +02:00
Sven Mika
a2a077b874
[RLlib] Faster remote worker space inference (don't infer if not required). ( #18805 )
2021-09-23 10:54:37 +02:00
Sven Mika
a96dbd885b
[RLlib] Reinstate trajectory view API tests. ( #18809 )
2021-09-23 08:31:51 +02:00
Sven Mika
93208bb087
[RLlib] Increase size of (very flakey) action_masking example script test. ( #18816 )
2021-09-22 21:48:01 +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
e6aae61487
[RLlib; testing] Fix bug in stress tests not handling >1 trials per experiment (due to grid-search in IMPALA stress tests). ( #18705 )
2021-09-20 15:31:57 +02:00
Sven Mika
fd13bac9b3
[RLlib] Add worker arg (optional) to policy_mapping_fn. ( #18184 )
2021-09-17 12:07:11 +02:00
Sven Mika
ba1c489b79
[RLlib Testing] Lower --smoke-test "time_total_s" to make sure it doesn't time out. ( #18670 )
2021-09-16 18:22:23 +02:00
Sven Mika
8a72824c63
[RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). ( #18591 )
2021-09-15 22:16:48 +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
Sven Mika
c5d20849ae
[RLlib] Rename rllib rollout into rllib evaluate (backward compatible) to match Trainer API. ( #18467 )
2021-09-15 08:45:17 +02:00
Sven Mika
08c09737fa
[RLlib] Fix R2D2 (torch) multi-GPU issue. ( #18550 )
2021-09-14 19:58:10 +02:00
Ameer Haj Ali
e6807ecb43
Change tests owners for ml tests ( #18417 )
2021-09-14 01:04:52 -07:00
Sven Mika
3803e796ff
[RLlib] Multi-GPU learner thread (IMPALA) error messages/comments/code-cleanup. ( #18540 )
2021-09-13 19:27:53 +02:00
