wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-21 12:50:45 +08:00
Code Issues Packages Projects Releases Wiki Activity
5,148 Commits 36 Branches 42 Tags
f080aa6ce33ed34f686e868d97b85632c8a8f894
Commit Graph
332 Commits
Author SHA1 Message Date
Sven MikaandGitHub 78dfed2683 [RLlib] Issue 8384: QMIX doesn't learn anything. (#9527) 2020-07-17 12:14:34 +02:00
Sven MikaandGitHub 8204717eed [RLlib] Issue 9218: PyTorch Policy places Model on GPU even with num_gpus=0 (#9516) 2020-07-17 05:53:25 +02:00
Michael LuoandGitHub 94fcd43593 [rllib] MAML Transform (#9463) 
* MAML Transform

* Moved Inner Adapt to Method in Execution Plan
 2020-07-16 11:11:33 -07:00
Sven MikaandGitHub 935d8308fb [RLlib] Issue #9437 (PyTorch converts to CPU tensor, even if on GPU). (#9497) 2020-07-16 14:55:50 +02:00
Sven MikaandGitHub 617eb8f279 [RLlib] Issue 9402 MARWIL producing nan rewards. (#9429) 2020-07-14 05:07:16 +02:00
Sven MikaandGitHub 03ab86567f [RLlib] Layout of Trajectory View API (new class: Trajectory; not used yet). (#9269) 2020-07-14 04:27:49 +02:00
Tanay WakhareandGitHub 15aa08a3d1 [RLLib] WindowStat bug fix (#9213) 
* WindowStat error catching, which processes NaNs properly instead of erroring. This ought to resolve issue #7910.
https://github.com/ray-project/ray/issues/7910
 2020-07-12 23:01:32 +02:00
Tanay WakhareandGitHub 3536d8e4b3 Masking error. With t*valid_mask, we get the error np.inf*0 = np.inf (#9407) 2020-07-12 22:59:35 +02:00
Sven MikaandGitHub fcdf410ae1 [RLlib] Tf2.x native. (#8752) 2020-07-11 22:06:35 +02:00
Sven MikaandGitHub 14160ca58c [RLlib] Issue #9366 (DQN w/o dueling produces invalid actions). (#9386) 2020-07-10 12:43:03 +02:00
Hao ChenandGitHub d49dadf891 Change Python's ObjectID to ObjectRef (#9353) 2020-07-10 17:49:04 +08:00
Sven MikaandGitHub 01125b8fcf [RLlib] DQN rainbow eager-mode (keras style NoisyLayer) (preparation for native tf2.x support). (#9304) 2020-07-09 10:44:10 +02:00
Sven MikaandGitHub 4da0e542d5 [RLlib] DDPG and SAC eager support (preparation for tf2.x) (#9204) 2020-07-08 16:12:20 +02:00
Benjamin BlackGitHubEric Liang
 		1425cdf834 Pettingzoo environment support (#9271) 
* added pettingzoo wrapper env and example

* added docs, examples for pettingzoo env support

* fixed pettingzoo env flake8, added test

* fixed pettingzoo env import

* fixed pettingzoo env import

* fixed pettingzoo import issue

* fixed pettingzoo test

* fixed linting problem

* fixed bad quotes

* future proofed pettingzoo dependency

* fixed ray init in pettingzoo env

* lint

* manual lint

Co-authored-by: Eric Liang <ekhliang@gmail.com>
 2020-07-06 21:32:26 -07:00
Piotr JanuszewskiandGitHub 155cc81e40 Clarify training intensity configuration docstring (#9244) (#9306) 2020-07-05 20:07:27 -07:00
Sven MikaandGitHub f43d934817 [RLlib] Type annotations for policy. (#9248) 2020-07-05 13:09:51 +02:00
Michael LuoandGitHub 851d02463b [Doc] RLlib Algorithms Documentation: MAML + PyTorch MAML (#9189) 2020-07-03 11:05:15 -07:00
Eric LiangandGitHub 4b62a888cc [rllib] Remove deprecated policy optimizer package. (#9262) 2020-07-02 14:39:40 -07:00
Sven MikaandGitHub 5b2a97597b [RLlib] Retire try_import_tree (should be installed along with other requirements). (#9211) 
- Retire try_import_tree.
- Stabilize test_supported_multi_agent.py.
 2020-07-02 13:06:34 +02:00
Sven MikaandGitHub c4ccbfdfa9 [RLlib] tf-eager support for ES and ARS (tf2.x preparation). (#9207) 2020-07-02 13:03:10 +02:00
Richard LiawandGitHub d35f0e40d0 [tune] Use public methods for trainable (#9184) 2020-07-01 11:00:00 -07:00
Sven MikaandGitHub b4c0b942fe [RLlib] Remove requirement for dataclasses in rllib (not supported in py3.5) (#9237) 2020-07-01 17:31:44 +02:00
Sven MikaandGitHub 43043ee4d5 [RLlib] Tf2x preparation; part 2 (upgrading try_import_tf()). (#9136) 
* WIP.

* Fixes.

* LINT.

* WIP.

* WIP.

* Fixes.

* Fixes.

* Fixes.

* Fixes.

* WIP.

* Fixes.

* Test

* Fix.

* Fixes and LINT.

* Fixes and LINT.

* LINT.
 2020-06-30 10:13:20 +02:00
Tanay WakhareandGitHub efcee9f1de [RLlib] MADDPG bug fix (issue https://github.com/ray-project/ray/issues/8483) (#9110) 
* Bug fix for https://githhub.com/ray-project/ray/issues/8483

We need to pass in a framework explicitly with the new defaults. Further, the actual bug was that policies were being sorted alphabetically in the MADDPG init(), which led to incorrect initialization.

* Linting
 2020-06-30 00:27:32 -07:00
Sven MikaandGitHub 0d37103f84 [RLlib] Prototype: Model Trajectory View API, part 0 (#9171) 2020-06-30 05:33:19 +02:00
Michael LuoandGitHub eb8eb2c71a [RLLib] DM Control Suite Wrapper and Examples (#9031) 
* DM Control Suite Added

* Added License

* Changes

* Test fixes
 2020-06-29 17:58:29 -07:00
Sven MikaandGitHub 5c6d5d4ab1 This PR fixes the currently broken lstm_use_prev_action_reward flag for default lstm models (model.use_lstm=True). (#8970) 2020-06-27 20:50:01 +02:00
Sven MikaandGitHub af1203b9df [RLlib] Issue 8507 (PyTorch does not support custom loss). (#9142) 2020-06-26 09:52:22 +02:00
Sven MikaandGitHub e93a1a82ab Issue 8407: RNN sequencing error in QMIX (#9139) 2020-06-26 09:50:31 +02:00
Sven MikaandGitHub 4fd8977eaf [RLlib] Minor cleanup in preparation to tf2.x support. (#9130) 
* WIP.

* Fixes.

* LINT.

* Fixes.

* Fixes and LINT.

* WIP.
 2020-06-25 19:01:32 +02:00
Sven MikaandGitHub aa231799ed Dyna test: small -> medium. (#9118) 2020-06-24 12:02:44 +02:00
Tanay WakhareandGitHub f77c638d6d Pytorch AttentionNet (#9088) 2020-06-23 20:42:30 +02:00
Michael LuoGitHubSven Mika
 		cf0894d396 [rllib] MAML Agent (#8862) 
* Halfway done with transferring MAML to new Ray

* MAML Beta Out

* Debugging MAML atm

* Distributed Execution

* Pendulum Mass Working

* All experiments complete

* Cleaned up codebase

* Travis CI

* Travis CI

* Tests

* Merged conflicts

* Fixed variance bug conflict

* Comment resolved

* Apply suggestions from code review

fixed test_maml

* Update rllib/agents/maml/tests/test_maml.py

* asdf

* Fix testing

Co-authored-by: Sven Mika <sven@anyscale.io>
 2020-06-23 09:48:23 -07:00
Sven MikaandGitHub 2589309cf0 [RLlib] Make sure torch and tf behave the same wrt conv2d nets. (#8785) 2020-06-20 00:05:19 +02:00
Max FittonandGitHub ad09aa985c Make Dashboard Port Configurable (#8999) 2020-06-19 16:26:22 -05:00
Eric LiangandGitHub 1e0e1a45e6 [rllib] Add type annotations for evaluation/, env/ packages (#9003) 2020-06-19 13:09:05 -07:00
Ian RodneyandGitHub 2e972c2a77 RLLIB and pylintrc (#8995) 2020-06-17 18:14:25 +02:00
Ian RodneyandGitHub 265ddfc2e4 blacklist to remove (#8994) 2020-06-17 18:02:28 +02:00
Joseph SuarezandGitHub c6ee3cdff4 Refactor #8792 to integrate latest master (#8956) 2020-06-17 10:55:52 +02:00
Sven MikaandGitHub 14405b90d5 [RLlib] Prototype of a DynaTrainer (for env dynamics learning in upcoming MBMPO algo). (#8860) 2020-06-16 09:01:20 +02:00
Sven MikaandGitHub 7008902cff [RLlib] Minor rllib.utils cleanup. (#8932) 2020-06-16 08:52:20 +02:00
Sven MikaandGitHub 0c7764b010 Issue 8919 checkpoint at end ignored (#8933) 2020-06-16 08:51:20 +02:00
Sven MikaandGitHub bdf1404a5f [RLlib] Issue 8714: QMIX init error w/ tuple obs space. (#8936) 2020-06-16 08:50:53 +02:00
Sven MikaandGitHub 4ed796a7d6 [RLlib] Add testing Policy.compute_single_action() for all agents. (#8903) 2020-06-13 17:51:50 +02:00
Eric LiangandGitHub 34bae27ac7 [rllib] Flexible multi-agent replay modes and replay_sequence_length (#8893) 2020-06-12 20:17:27 -07:00
Sven MikaandGitHub 8d1ccfd0f7 [RLlib] Issue 8889: action clipping bug ppo not learning mujoco (#8898) 2020-06-11 19:17:43 +02:00
Sven MikaandGitHub a90cd0fcbb [RLlib] Unity3d soccer benchmarks (#8834) 2020-06-11 14:29:57 +02:00
Kristian HolsheimerandGitHub ea965d7c52 [RLlib] use Mapping instead of dict in summarize() to accommodate non-dict grads/params (e.g. haiku's frozendict) (#8793) 2020-06-11 00:37:15 -07:00
Dean WamplerandGitHub 53712d2ef7 Fix typo in docs for LinearDiscreteEnv (#8891) 2020-06-11 08:34:35 +02:00
Sven MikaandGitHub 0ba7472da9 [Testing] Fix LINT/sphinx errors. (#8874) 2020-06-10 15:41:59 +02:00