Clark Zinzow
1a9ba19012
[Core] Adds deprecation decorator and fixes privatization of a few APIs. ( #14811 )
2021-03-22 10:31:50 -07:00
Kai Fricke
be30b784a4
Amend #14308 (fix for post_fcnet_hiddens) ( #14354 )
2021-03-22 15:44:18 +01:00
Chris Bamford
cd89f0dc55
[RLLib] Episode media logging support ( #14767 )
2021-03-19 09:17:09 +01:00
Ian Rodney
eb12033612
[Code Cleanup] Switch to use ray.util.get_node_ip_address() ( #14741 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2021-03-18 13:10:57 -07:00
Sven Mika
c3a15ecc0f
[RLlib] Issue #13802 : Enhance metrics for multiagent->count_steps_by=agent_steps setting. ( #14033 )
2021-03-18 20:27:41 +01:00
Sven Mika
69202c6a7d
[RLlib] Obsolete usage tracking dict via sample batch. ( #13065 )
2021-03-17 08:18:15 +01:00
Sven Mika
78a134efa2
[RLlib] Add HowTo set env seed to our custom env example script. ( #14471 )
2021-03-16 08:12:27 +01:00
Sven Mika
4e17f95927
[RLlib] Unflake 2 test cases (SAC cont. cartpole). ( #14620 )
2021-03-15 14:03:54 +01:00
Sven Mika
ee4b6e7e3b
[RLlib] Unity3D example broken due to change in ML-Agents API. Attention-net prev-n-a/r. Attention-wrapper works with images. ( #14569 )
2021-03-12 18:27:25 +01:00
Michael Luo
020c9439dd
[RLlib] CQL Documentation + Tests ( #14531 )
2021-03-11 18:51:39 +01:00
Clark Zinzow
5a788474aa
[Core] First pass at privatizing non-public Python APIs. ( #14607 )
...
* async_compat
* utils
* cluster_utils
* compat
* function_manager
* import_thread
* memory_monitor
* monitor, log_monitor, ray_process_reaper
* metrics_agent
* parameter
* prometheus_exporter
* ray_logging
* signature
2021-03-10 22:47:28 -08:00
Maxime RICHE
9a7fbd3cdf
[RLlib] Add coin game env. Matrix social dilemma env. With tests and examples. ( #14208 )
2021-03-09 17:26:20 +01:00
Sven Mika
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. ( #13393 )
2021-03-08 15:41:27 +01:00
Sven Mika
ef944bc5f0
[RLlib] Re-enable placement group support for RLlib. ( #14384 )
2021-03-05 08:16:24 +01:00
Sven Mika
5637d89ecc
[RLlib] Serve + RLlib example script. ( #14416 )
2021-03-03 14:33:03 +01:00
Sven Mika
7718ec70fb
[RLlib] Remove old SegmentTree from tests dir and unflake respective segment tree test. ( #14450 )
2021-03-03 14:31:30 +01:00
Eric Liang
9db000ff2c
Auto report object store memory usage; remove some deprecated code ( #14260 )
2021-03-01 13:19:44 -08:00
Kai Fricke
7f9340bb2f
[tune] Add leading zeros to checkpoint directory ( #14152 )
...
* [tune] Add leading zeros to checkpoint directory
* Fix exp analysis tests/support string indices
* Fix tests
* RLLib tests
2021-03-01 12:12:19 +01:00
Richard Liaw
a2d2275ee1
Revert "[RLlib + Tune] Add placement group support to RLlib. ( #14289 )" ( #14360 )
...
This reverts commit 6cd0cd3bd9
2021-02-25 14:27:35 -08:00
Sven Mika
4cd5c1da2c
[RLlib] Remove flaky test case for mixed (tf+torch) policies trainer. ( #14357 )
2021-02-25 14:07:05 -08:00
Sven Mika
6cd0cd3bd9
[RLlib + Tune] Add placement group support to RLlib. ( #14289 )
2021-02-25 16:01:31 +01:00
Sven Mika
8000258333
[RLlib] R2D2 Implementation. ( #13933 )
2021-02-25 12:18:11 +01:00
Kai Fricke
d9e5d5f47a
[RLlib] Cast fcnet_hiddens to list for DQN models (list vs tuple mismatch error) ( #14308 )
2021-02-25 08:06:08 +01:00
Michael Luo
ec2c10309b
[RLlib] CQL for HalfCheetah-Random-v0 + Hopper-Random-v0 + CQL Bug Fixes ( #14243 )
2021-02-22 17:30:18 +01:00
Sven Mika
95ef04b71a
[RLlib] Implement TorchPolicy.export_model. ( #13989 )
2021-02-22 17:09:40 +01:00
Sven Mika
3d20d58c90
[RLlib] Tune trial + checkpoint selection example. ( #14209 )
2021-02-22 12:52:37 +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
929946271d
[RLlib] Issue #14022 : Trajectory View API fails in MA-env where a new agent terminates right away (done=True right after initial obs). ( #14031 )
2021-02-18 14:07:49 +01:00
Sven Mika
4db86404ad
[RLlib] Issue #13507 : Fix MB-MPO CartPole Env's reward function as well as MB-MPO running into a traj. view API related issue. ( #14037 )
2021-02-11 18:58:46 +01:00
Sven Mika
a2f7998026
[RLlib] Issue #13342 : Add validate_spaces to MB-MPO. ( #14038 )
2021-02-11 11:36:53 +01:00
Sven Mika
81e7434091
[RLlib] TFPolicy.export_model: Add timestep placeholder to model's signature, if needed. ( #13988 )
2021-02-10 15:21:46 +01:00
Sven Mika
37c7daa3c0
[RLlib] DDPG: Support simplex action space. ( #14011 )
2021-02-10 15:10:01 +01:00
Sven Mika
d7301a51f4
[RLlib]: Trajectory View API: Keep env infos (e.g. for postprocessing callbacks), no matter what. ( #13555 )
2021-02-09 17:05:26 +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
Chace Ashcraft
ebeee1d59a
[RLlib] Pytorch MAML fix for more than two workers with discrete actions ( #13835 )
2021-02-08 12:06:02 +01:00
Sven Mika
d001af3e59
[RLlib] Allow rllib rollout to run distributed via evaluation workers. ( #13718 )
2021-02-08 12:05:16 +01:00
Sven Mika
9ac731558b
[RLlib] Unify fcnet initializers for the value output layer (std=1.0 in torch, but 0.01 in tf). ( #13733 )
2021-02-02 18:42:49 +01:00
Sven Mika
0a0d9183fe
[RLlib] Trajectory view API example script (enhancements and tf2 support). ( #13786 )
2021-02-02 18:42:18 +01:00
Stanislav Chekmenev
b9c15a2551
[RLlib] Issue #13761 : Fix get action shape ( #13764 )
2021-02-02 13:13:43 +01:00
Raoul Khouri
714c367b9d
[RLlib] Trainer._validate_config idempotentcy correction (issue 13427) ( #13556 )
2021-02-02 13:11:57 +01:00
Sven Mika
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. ( #13522 )
2021-02-02 13:05:58 +01:00
Sven Mika
4bc257f4fb
[RLlib] Fix custom multi action distr ( #13681 )
2021-01-28 19:28:48 +01:00
Yuri Rocha
b01b0f80aa
[RLlib] Fix multiple Unity3DEnvs trying to connect to the same custom port ( #13519 )
2021-01-28 13:28:08 +01:00
cathrinS
d4ef5c5993
[RLlib] Atari-RAM-Preprocessing, unsigned observation vector results in a false preprocessed observation ( #13013 )
2021-01-28 12:07:00 +01:00
Maltimore
b4702de1c2
[RLlib] move evaluation to trainer.step() such that the result is properly logged ( #12708 )
2021-01-25 12:56:00 +01:00
Jan Blumenkamp
964689b280
[RLlib] Fix bug in ModelCatalog when using custom action distribution ( #12846 )
...
* return tuple returned from _get_multi_action_distribution when using custom action dict
* Always return dst_class and required_model_output_shape in _get_multi_action_distribution
* pass model config to _get_multi_action_distribution
2021-01-25 12:42:39 +01:00
Sven Mika
9423930bcc
[RLlib] MAML: Add cartpole mass test for PyTorch. ( #13679 )
2021-01-25 12:32:41 +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
Michael Luo
587f207c2f
[RLlib] Support for D4RL + Semi-working CQL Benchmark ( #13550 )
2021-01-21 16:43:55 +01:00
Saeid
d11e62f9e6
[RLlib] Fix problem in preprocessing nested MultiDiscrete ( #13308 )
2021-01-21 16:36:11 +01:00
