wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-17 11:32:33 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,214 Commits 36 Branches 42 Tags
91fa7e0b4e8f2dd997b855952e4e8e3bdc0bdb5c
Commit Graph
443 Commits
Author SHA1 Message Date
mvindiola1andGitHub 9e68b77796 [RLLIB] Wait for remote_workers to finish closing environments before terminating (#11476) 2020-10-28 14:23:06 -07:00
Sven MikaandGitHub d9f1874e34 [RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609) 2020-10-27 10:00:24 +01:00
Kingsley KuanandGitHub d1dd5d578e [RLlib] Fix PyTorch A3C / A2C loss function using mixed reduced sum / mean (#11449) 2020-10-22 12:39:34 -07:00
Philsik ChangandGitHub ede9347127 [rllib] Add torch_distributed_backend flag for DDPPO (#11362) (#11425) 2020-10-21 18:30:42 -07:00
Eric LiangandGitHub e8c77e2847 Remove memory quota enforcement from actors (#11480) 
* wip

* fix

* deprecate
 2020-10-21 14:29:03 -07:00
Sven MikaandGitHub 2aec77e305 [RLlib] Fix two test cases that only fail on Travis. (#11435) 2020-10-16 13:53:30 -05:00
Sven MikaandGitHub 414041c6dd [RLlib] Do not create env on driver iff num_workers > 0. (#11307) 2020-10-15 18:21:30 +02:00
Sven MikaandGitHub a6a94d3206 [RLlib] Fix test_env_with_subprocess.py. (#11356) 2020-10-13 12:42:20 -07:00
Sven MikaandGitHub 1ebcdf236f [RLlib] Add support for custom MultiActionDistributions. (#11311) 2020-10-12 13:50:43 -07:00
Sven MikaandGitHub 0c0f67c14d [RLlib] ARS/ES eval workers not working: Issue 9933. (#11308) 2020-10-12 13:49:48 -07:00
Sven MikaandGitHub 8ea1bc5ff9 [RLlib] Allow for more than 2^31 policy timesteps. (#11301) 2020-10-12 13:49:11 -07:00
Sven MikaandGitHub f5e2cda68a [RLlib] SAC: log_alpha not being learnt when on GPU. (#11298) 2020-10-12 13:48:44 -07:00
Julius FrostandGitHub 7dcfd258cd [RLlib] Assert LongTensor in SAC Discrete PyTorch (#11245) 2020-10-12 13:47:21 -07:00
Sven MikaandGitHub d3bc20b727 [RLlib] ConvTranspose2D module (#11231) 2020-10-12 15:00:42 +02:00
Sven MikaandGitHub 957877ad3f Tf version of VisionNet (ray/rllib/model/tf/vision_net.py) crashes iff len(conv-filters)=1. (#11330) 2020-10-11 12:49:47 +02:00
Thomas TumielGitHubRichard Liaw
 		587319debc [tune] move _SCHEDULERS to tune.schedulers and add all available schedulers (#11218) 
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
 2020-10-08 16:10:23 -07:00
desktableandGitHub 8af9ff6dc2 [RLlib] Add MultiAgentEnv wrapper for Kaggle's football environment (#11249) 
* [RLlib] Add MultiAgentEnv wrapper for Kaggle's football environment

* Add unit tests to BUILD

* Add gfootball dependency

* Revert the last two commits
 2020-10-08 10:57:58 -07:00
desktableandGitHub f9621ce23c [RLlib] Add recsim_wrapper unit test to BUILD (#11225) 2020-10-08 08:23:27 +02:00
Sumanth RatnaandGitHub 14d8826e43 Fix overriden typo (#11227) 2020-10-07 19:11:07 -07:00
Anes BenmerzougandGitHub ff3e411ea2 [rllib] Fix VectorEnv's check for the info object's type (#10982) 2020-10-07 15:00:37 -07:00
Edward OakesandGitHub cd6936e60b Deflake test_env_with_subprocess.py (#11257) 2020-10-07 16:19:40 -05:00
Sven MikaandGitHub 199e5d0f75 [RLlib] Exploration class type annotations. (#11251) 2020-10-07 21:59:14 +02:00
Sven MikaandGitHub ce96b03b07 [RLlib] MB-MPO cleanup (comments, docstrings, type annotations). (#11033) 2020-10-06 20:28:16 +02:00
Philsik ChangandGitHub 2b26d2ca1b [rllib] Fix for Torch checkpoint taken on GPU fails to deserialize on CPU (#11071) (#11208) 2020-10-05 22:01:55 -07:00
desktableandGitHub 56b56cf7a1 [RLlib] Add RecSim environment wrapper (#11205) 2020-10-05 09:05:02 +02:00
Sven MikaandGitHub c17169dc11 [RLlib] Fix all example scripts to run on GPUs. (#11105) 2020-10-02 23:07:44 +02:00
Michael LuoandGitHub 47b499d899 Cartpole MAML + Discrete (#11028) 2020-10-02 12:56:34 +02:00
Sven MikaandGitHub 36bda8432b [RLlib] Trajectory view API: Simple List Collector (on by default for PPO); LSTM-agnostic (#11056) 2020-10-01 16:57:10 +02:00
Benjamin BlackandGitHub 4445f32798 [rllib] Fixed pettingzoo wrapper (#11060) 
* fixed PettingZooEnv, relevant docs, examples

* fixed linting error

* pettingzoo wrapper fix

* fixed linting issue
 2020-09-30 15:34:47 -07:00
Sven MikaandGitHub 47eb6613b5 [RLlib] Remove unnecessary copies in compute_advantages. (#10897) 2020-09-29 12:25:20 +02:00
Sven MikaandGitHub f91c455527 [RLlib] Curiosity documentation. (#11066) 2020-09-29 09:39:22 +02:00
Eric LiangandGitHub 8f79b4e45e [rllib] Replay buffer size inaccurate with replay_seq_len option (#10988) 
* support replay seq len

* update

* fix warn

* add test

* test
 2020-09-25 13:47:23 -07:00
Eric LiangandGitHub 609c1b8acd Start moving ray internal files to _private module (#10994) 2020-09-24 22:46:35 -07:00
Eric LiangandGitHub ecdaaffc67 add large data warning (#10957) 2020-09-23 15:46:06 -07:00
Michael LuoandGitHub ba5a3ae9e2 Enable vtrace by default (#10962) 2020-09-22 22:18:21 -07:00
Eric LiangandGitHub daa03ba6e6 [rllib] Add execution module to package ref (#10941) 
* add init

* add

* update
 2020-09-21 23:03:06 -07:00
internetcoffeephoneandGitHub 840fb5543b Change get_action_shape so that it uses the dtype of the Discrete object, rather than overwriting it with tf.int64. (#8424) 2020-09-21 17:08:31 -07:00
mvindiola1GitHubManny Vindiola
 		2b893d1bb5 fix incorrect critic loss in TD3 (#10775) 
Co-authored-by: Manny Vindiola <manuel.m.vindiola.civ@mail.mil>
 2020-09-20 20:01:51 -07:00
Sven MikaandGitHub d7c42d6d92 [RLlib] Unity blogpost final fixes. (#10894) 2020-09-20 14:13:20 +02:00
Sven MikaandGitHub 805dad3bc4 [RLlib] SAC algo cleanup. (#10825) 2020-09-20 11:27:02 +02:00
Sumanth RatnaandGitHub 9da7bdcc8e Use master for links to docs in source (#10866) 2020-09-19 00:30:45 -07:00
Benjamin BlackandGitHub f2408b719c Fixed PettingZooEnv (#10847) 2020-09-17 11:28:42 -07:00
Sven MikaandGitHub 5c7b35d694 [RLlib] Issue 10833 TorchPolicy GPU. (#10834) 2020-09-17 09:04:46 +02:00
Eric LiangandGitHub f83c588f08 [rllib] Remove broken no eager on workers mode (#10745) 
* remove no eager

* Update trainer.py
 2020-09-15 17:25:20 -07:00
desktableandGitHub 4ccfd07a61 [RLlib] Add docstrings for agents/dqn (#10710) 2020-09-15 12:37:07 +02:00
Richard LiawandGitHub 6662efd74b [tune/rllib] revert removal of queue-trials (#10744) 2020-09-11 14:13:20 -07:00
maxco2andGitHub b8436f0f00 [rllib] Fix SAC and DDPG tensorflow policy can't do grad_clip (#10499) 
* Fix sac_tf_policy clip_by_norm missing argument

* Fix ddpg_tf_policy clip_by_norm missing argument

* Fix format
 2020-09-11 12:04:44 -07:00
Thomas LecatandGitHub 504da45e69 fix(rllib): allow explore=False with tuple action distributions (#10443) 2020-09-10 15:03:02 -07:00
Julius FrostandGitHub 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
desktableandGitHub 799318d7d7 [RLlib] Add type annotations for agents/dqn (#10626) 2020-09-09 18:55:26 +02:00