Commit graph

752 commits

Author SHA1 Message Date
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
78c64ca151
[RLlib] Attention net example script: Clarifications on how to use with Trainer.compute_action. (#14864) 2021-03-23 19:33:01 +01:00
Sven Mika
04bc0a9828
[RLlib] Remove all non-trajectory view API code. (#14860) 2021-03-23 09:50:18 -07:00
Sven Mika
3e7899d251
[RLlib] Issue 14653: Empty env steps cause key error in SimpleListCollector. (#14765) 2021-03-23 10:30:53 +01:00
Sven Mika
f859ebb99f
[RLlib] Fix env rendering and recording options (for non-local mode; >0 workers; +evaluation-workers). (#14796) 2021-03-23 10:06:06 +01:00
Sven Mika
e7557ae433
[RLlib] Issue 13132: DQN does not update target net after restore (#14838) 2021-03-23 08:30:37 +01:00
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