wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-09 02:10:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,359 Commits 36 Branches 42 Tags
8fb926565cbf0cd554bc24ccf1ea3a47dcc41dad
Commit Graph

466 Commits

Author SHA1 Message Date
Michael Luo 59bc1e6c09 [RLLib] MAML extension for all models except RNNs (#11337) 2020-11-12 16:51:40 -08:00
Sven Mika 0bd69edd71 [RLlib] Trajectory view API: enable by default for ES and ARS (#11826) 2020-11-12 10:33:10 -08:00
Michael Luo 6e6c680f14 MBMPO Cartpole (#11832) 
* MBMPO Cartpole Done

* Added doc
 2020-11-12 10:30:41 -08:00
Sven Mika 62c7ab5182 [RLlib] Trajectory view API: Enable by default for PPO, IMPALA, PG, A3C (tf and torch). (#11747) 2020-11-12 16:27:34 +01:00
Michael Luo 59ccbc0fc7 [RLlib] Model Annotations: Tensorflow (#11964) 2020-11-12 12:18:50 +01:00
Michael Luo b2984d1c34 [RLlib] Model Annotations to Torch Models (#9749) 2020-11-12 12:16:12 +01:00
Sven Mika 72fc79740c [RLlib] Issue with pickle versions (breaks rollout test cases in RLlib). (#11939) 2020-11-11 21:52:21 +01:00
Sven Mika 291c172d83 [RLlib] Support Simplex action spaces for SAC (torch and tf). (#11909) 2020-11-11 18:45:28 +01:00
Eric Liang 9b8218aabd [docs] Move all /latest links to /master (#11897) 
* use master link

* remae

* revert non-ray

* more

* mre
 2020-11-10 10:53:28 -08:00
Benjamin Black 1999266bba Updated pettingzoo env to acomidate api changes and fixes (#11873) 
* Updated pettingzoo env to acomidate api changes and fixes

* fixed test failure

* fixed linting issue

* fixed test failure
 2020-11-09 16:09:49 -08:00
Eric Liang 6b7a4dfaa0 [rllib] Forgot to pass ioctx to child json readers (#11839) 
* fix ioctx

* fix
 2020-11-05 22:07:57 -08:00
Sven Mika d6c7c7c675 [RLlib] Make sure, DQN torch actions are of type=long before torch.nn.functional.one_hot() op. (#11800) 2020-11-04 18:04:03 +01:00
heng2j 9073e6507c WIP: Update to support the Food Collector environment (#11373) 
* Update to support the Food Collector environment 

Recently, I am trying out ML Agent with Ray, and trying to use the food collector environment. Since the observation space and action space haven't defined in the unity3d_env.py. I propose to make this changes to add the support for Food Collector. I have tried to use this env in the [unity3d_env_local example](https://github.com/ray-project/ray/blob/master/rllib/examples/unity3d_env_local.py). Please let me know if this the proper adjustment. Even these are just few line of code, please let me know how can I made a proper contribution.

* Apply suggestions from code review
 2020-11-04 12:29:16 +01:00
Pierre TASSEL 66605cfcbd [RLLib] Random Parametric Trainer (#11366) 2020-11-04 11:12:51 +01:00
mvindiola1 4518fe790f [RLLIB] Convert torch state arrays to tensors during compute log likelihoods (#11708) 2020-11-04 09:33:56 +01:00
Sven Mika 5b788ccb13 [RLlib] Trajectory view API (prep PR for switching on by default across all RLlib; plumbing only) (#11717) 2020-11-03 12:53:34 -08:00
desktable 5af745c90d [RLlib] Implement the SlateQ algorithm (#11450) 2020-11-03 09:52:04 +01:00
Lara Codeca e735add268 [RLlib] Integration with SUMO Simulator (#11710) 2020-11-03 09:45:03 +01:00
dHannasch 8346dedc3a Fix the linter failure. (#11755) 2020-11-02 18:02:15 +01:00
bcahlit 26176ec570 [RLlib] Fix epsilon_greedy on nested_action_spaces only in pytorch (#11453) 
* [RLlib] Fix epsilon_greedy on nested_action_spaces only in pytorch

* epsilon_greedy on Continuous action

* formatt

* Fix error

* fix format

* fix bug

* increase speed

* Update rllib/utils/exploration/epsilon_greedy.py

* Update rllib/utils/exploration/epsilon_greedy.py

* Update rllib/utils/exploration/epsilon_greedy.py

Co-authored-by: Sven Mika <sven@anyscale.io>
 2020-11-02 12:22:33 +01:00
Sven Mika 54d85a6c2a [RLlib] Fix RNN learning for tf-eager/tf2.x. (#11720) 2020-11-02 11:18:41 +01:00
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
Jiajie Xiao 0b07af374a allow tuple action space (#11429) 
Co-authored-by: Jiajie Xiao <jj@Jiajies-MBP-2.attlocal.net>
 2020-10-29 16:05:38 +01:00
mvindiola1 9e68b77796 [RLLIB] Wait for remote_workers to finish closing environments before terminating (#11476) 2020-10-28 14:23:06 -07:00
Sven Mika d9f1874e34 [RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609) 2020-10-27 10:00:24 +01:00
Kingsley Kuan d1dd5d578e [RLlib] Fix PyTorch A3C / A2C loss function using mixed reduced sum / mean (#11449) 2020-10-22 12:39:34 -07:00
Philsik Chang ede9347127 [rllib] Add torch_distributed_backend flag for DDPPO (#11362) (#11425) 2020-10-21 18:30:42 -07:00
Eric Liang e8c77e2847 Remove memory quota enforcement from actors (#11480) 
* wip

* fix

* deprecate
 2020-10-21 14:29:03 -07:00
Sven Mika 2aec77e305 [RLlib] Fix two test cases that only fail on Travis. (#11435) 2020-10-16 13:53:30 -05:00
Sven Mika 414041c6dd [RLlib] Do not create env on driver iff num_workers > 0. (#11307) 2020-10-15 18:21:30 +02:00
Sven Mika a6a94d3206 [RLlib] Fix test_env_with_subprocess.py. (#11356) 2020-10-13 12:42:20 -07:00
Sven Mika 1ebcdf236f [RLlib] Add support for custom MultiActionDistributions. (#11311) 2020-10-12 13:50:43 -07:00
Sven Mika 0c0f67c14d [RLlib] ARS/ES eval workers not working: Issue 9933. (#11308) 2020-10-12 13:49:48 -07:00
Sven Mika 8ea1bc5ff9 [RLlib] Allow for more than 2^31 policy timesteps. (#11301) 2020-10-12 13:49:11 -07:00
Sven Mika f5e2cda68a [RLlib] SAC: log_alpha not being learnt when on GPU. (#11298) 2020-10-12 13:48:44 -07:00
Julius Frost 7dcfd258cd [RLlib] Assert LongTensor in SAC Discrete PyTorch (#11245) 2020-10-12 13:47:21 -07:00
Sven Mika d3bc20b727 [RLlib] ConvTranspose2D module (#11231) 2020-10-12 15:00:42 +02:00
Sven Mika 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 Tumiel 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
desktable 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
desktable f9621ce23c [RLlib] Add recsim_wrapper unit test to BUILD (#11225) 2020-10-08 08:23:27 +02:00
Sumanth Ratna 14d8826e43 Fix overriden typo (#11227) 2020-10-07 19:11:07 -07:00
Anes Benmerzoug ff3e411ea2 [rllib] Fix VectorEnv's check for the info object's type (#10982) 2020-10-07 15:00:37 -07:00
Edward Oakes cd6936e60b Deflake test_env_with_subprocess.py (#11257) 2020-10-07 16:19:40 -05:00
Sven Mika 199e5d0f75 [RLlib] Exploration class type annotations. (#11251) 2020-10-07 21:59:14 +02:00
Sven Mika ce96b03b07 [RLlib] MB-MPO cleanup (comments, docstrings, type annotations). (#11033) 2020-10-06 20:28:16 +02:00
Philsik Chang 2b26d2ca1b [rllib] Fix for Torch checkpoint taken on GPU fails to deserialize on CPU (#11071) (#11208) 2020-10-05 22:01:55 -07:00
desktable 56b56cf7a1 [RLlib] Add RecSim environment wrapper (#11205) 2020-10-05 09:05:02 +02:00
Sven Mika c17169dc11 [RLlib] Fix all example scripts to run on GPUs. (#11105) 2020-10-02 23:07:44 +02:00
Michael Luo 47b499d899 Cartpole MAML + Discrete (#11028) 2020-10-02 12:56:34 +02:00