wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-28 11:25:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,359 Commits 36 Branches 42 Tags
8fb926565cbf0cd554bc24ccf1ea3a47dcc41dad
Commit Graph
132 Commits
Author SHA1 Message Date
Sven MikaandGitHub 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
mvindiola1andGitHub 4518fe790f [RLLIB] Convert torch state arrays to tensors during compute log likelihoods (#11708) 2020-11-04 09:33:56 +01:00
Sven MikaandGitHub 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
Sven MikaandGitHub 54d85a6c2a [RLlib] Fix RNN learning for tf-eager/tf2.x. (#11720) 2020-11-02 11:18:41 +01:00
Sven MikaandGitHub d9f1874e34 [RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609) 2020-10-27 10:00:24 +01:00
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 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
Sven MikaandGitHub c17169dc11 [RLlib] Fix all example scripts to run on GPUs. (#11105) 2020-10-02 23:07:44 +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
Eric LiangandGitHub ecdaaffc67 add large data warning (#10957) 2020-09-23 15:46:06 -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
Sven MikaandGitHub 5c7b35d694 [RLlib] Issue 10833 TorchPolicy GPU. (#10834) 2020-09-17 09:04:46 +02:00
desktableandGitHub 799318d7d7 [RLlib] Add type annotations for agents/dqn (#10626) 2020-09-09 18:55:26 +02:00
Sven MikaandGitHub 28ab797cf5 [RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). (#10544) 2020-09-06 10:58:00 +02:00
Sven MikaandGitHub ef18893fb5 [RLlib] PPO, APPO, and DD-PPO code cleanup. (#10420) 2020-09-02 14:03:01 +02:00
Michael LuoandGitHub 4e9888ce2f [RLlib] Dreamer (#10172) 2020-08-26 13:24:05 +02:00
Sven MikaandGitHub e968b52cb7 [RLlib] Trajectory view API - 03 Fast LSTM + prev actions/rewards (#9950) 2020-08-21 12:35:16 +02:00
Sven MikaandGitHub d14b501692 [RLlib] First attempt at cleaning up algo code in RLlib: PG. (#10115) 2020-08-20 17:05:57 +02:00
Sven MikaandGitHub 2cbe29a7fa [RLlib] Curiosity minor fixes, do-overs, and testing. (#10143) 2020-08-19 17:49:50 +02:00
Eric LiangandGitHub ca133e2699 [rllib] Remove extra model config kwargs passed incorrectly for Torch models (#10055) 2020-08-17 11:12:20 -07:00
Olli HuotariandGitHub 9ff599cbb8 torch policy now includes model.metrics (#10121) 
* torch policy now includes model.metrics

* Fixed tests to work with custom metrics

* Forgot to run format.sh
 2020-08-15 10:43:11 -07:00
Sven MikaandGitHub aeb5be7733 [RLlib] Trajectory View API (part 2.5): Actual implementations (not used yet) of a SampleCollector. (#10112) 2020-08-15 15:09:00 +02:00
Sven MikaandGitHub 2256047876 [RLlib] Rename rllib.utils.types into typing to match built-in python module's name. (#10114) 2020-08-15 13:24:22 +02:00
Tanay WakhareandGitHub 1826b29757 [RLlib] Curiosity (intrinsic motivation) Exploration module. (#9912) 2020-08-13 20:14:16 +02:00
yncxcwGitHubRichard Liaw
 		32cd94b750 [Core] Do not convert gpu id to int (#9744) 
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
 2020-08-11 12:09:46 -07:00
Barak MichenerandGitHub 8e76796fd0 ci: Redo format.sh --all script & backfill lint fixes (#9956) 2020-08-07 16:49:49 -07:00
Eric LiangandGitHub 668f555755 [rllib] Clean up outdated docs #9915 2020-08-06 18:29:04 -07:00
Sven MikaandGitHub 57690a3a9f [RLlib] Trajectory view API - 02 actual API scaffold (#9753) 2020-08-06 10:54:20 +02:00
Sven MikaandGitHub 9b90f7db67 [RLlib] Missing type annotations policy templates. (#9846) 2020-08-06 05:33:24 +02:00
Sven MikaandGitHub b0b0463161 [RLlib] Trajectory View API (preparatory cleanup and enhancements). (#9678) 2020-07-29 21:15:09 +02:00
Eric LiangandGitHub 590943a499 [rllib] Type annotations for model classes (#9646) 2020-07-24 12:01:46 -07:00
Eric LiangandGitHub 5acd3e66dd [rllib] Fix torch TD error, IMPALA LR updates (#9477) 
* update

* add test

* lint

* fix super call

* speed es test up
 2020-07-23 12:50:25 -07:00
Raphael AvalosandGitHub 440c9c42be [RLlib] Fix combination of lockstep and multiple agnts controlled by the same policy. (#9521) 
* Change aggregation when lockstep is activated.

Modification of MultiAgentBatch.timeslices to support the combination of lockstep and multiple agents controlled by the same policy.

fix ray-project/ray#9295

* Line too long.
 2020-07-19 23:03:12 -07:00
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
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 03ab86567f [RLlib] Layout of Trajectory View API (new class: Trajectory; not used yet). (#9269) 2020-07-14 04:27:49 +02:00
Sven MikaandGitHub fcdf410ae1 [RLlib] Tf2.x native. (#8752) 2020-07-11 22:06:35 +02:00
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
Sven MikaandGitHub f43d934817 [RLlib] Type annotations for policy. (#9248) 2020-07-05 13:09:51 +02:00
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 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
Sven MikaandGitHub 0d37103f84 [RLlib] Prototype: Model Trajectory View API, part 0 (#9171) 2020-06-30 05:33:19 +02:00
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 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