internetcoffeephone
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
mvindiola1
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 Mika
d7c42d6d92
[RLlib] Unity blogpost final fixes. ( #10894 )
2020-09-20 14:13:20 +02:00
Sven Mika
805dad3bc4
[RLlib] SAC algo cleanup. ( #10825 )
2020-09-20 11:27:02 +02:00
Sumanth Ratna
9da7bdcc8e
Use master for links to docs in source ( #10866 )
2020-09-19 00:30:45 -07:00
Benjamin Black
f2408b719c
Fixed PettingZooEnv ( #10847 )
2020-09-17 11:28:42 -07:00
Sven Mika
5c7b35d694
[RLlib] Issue 10833 TorchPolicy GPU. ( #10834 )
2020-09-17 09:04:46 +02:00
Eric Liang
f83c588f08
[rllib] Remove broken no eager on workers mode ( #10745 )
...
* remove no eager
* Update trainer.py
2020-09-15 17:25:20 -07:00
desktable
4ccfd07a61
[RLlib] Add docstrings for agents/dqn ( #10710 )
2020-09-15 12:37:07 +02:00
Richard Liaw
6662efd74b
[tune/rllib] revert removal of queue-trials ( #10744 )
2020-09-11 14:13:20 -07:00
maxco2
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 Lecat
504da45e69
fix(rllib): allow explore=False with tuple action distributions ( #10443 )
2020-09-10 15:03:02 -07:00
Julius Frost
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
desktable
799318d7d7
[RLlib] Add type annotations for agents/dqn ( #10626 )
2020-09-09 18:55:26 +02:00
Sven Mika
4b278c36fc
[RLlib] Behavioral Cloning (from MARWIL). ( #10619 )
2020-09-09 17:33:21 +02:00
Michael Luo
8e613652af
[RLLib] MBMPO Fixes ( #10296 )
2020-09-09 09:34:34 +02:00
Alex Wu
a699f6a4d8
[Core] Fix override memory and object_store_memory in decorator ( #10563 )
2020-09-06 20:56:48 -07:00
Sven Mika
28ab797cf5
[RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). ( #10544 )
2020-09-06 10:58:00 +02:00
Richard Liaw
551c597312
[tune] API revamp fix ( #10518 )
2020-09-05 15:34:53 -07:00
Sven Mika
8a891b3c30
[RLlib] SAC n_step > 1. ( #10567 )
2020-09-05 22:26:42 +02:00
Sven Mika
244aafdcf8
[RLlib] Curiosity enhancements. ( #10373 )
2020-09-05 13:14:24 +02:00
architkulkarni
6ae9e76b81
[RLlib] Fix seeding issue ( #10589 )
2020-09-04 17:17:53 -07:00
Justin Terry
352718610d
Multi-agent Algorithm Documentation Updates ( #9722 )
2020-09-03 22:37:46 -07:00
Sven Mika
715ee8dfc9
[RLlib] Issue 10469: Callbacks should receive env idx ... ( #10477 )
2020-09-03 17:27:05 +02:00
Sven Mika
ef18893fb5
[RLlib] PPO, APPO, and DD-PPO code cleanup. ( #10420 )
2020-09-02 14:03:01 +02:00
Eric Liang
2a204260a8
[api] Second round of 1.0 API changes: exceptions, num_return_vals ( #10377 )
2020-08-28 19:57:02 -07:00
Eric Liang
519354a39a
[api] Initial API deprecations for Ray 1.0 ( #10325 )
2020-08-28 15:03:50 -07:00
Sven Mika
93120e0347
Unity3D API Fixes (recent changes in Unity's MLAgents API caused errors on RLlib side). ( #10285 )
2020-08-26 14:16:08 +02:00
Michael Luo
4e9888ce2f
[RLlib] Dreamer ( #10172 )
2020-08-26 13:24:05 +02:00
Olli Huotari
0dae50b5eb
Fixed num_atoms>1 in pytorch ( #10330 )
2020-08-25 23:10:20 -07:00
Eric Liang
deea1861ab
[rllib] Try fixing torch GPU and masking errors ( #10168 )
2020-08-25 18:34:19 -07:00
Benjamin Black
2689fb439c
Fixed pettingzoo env example ( #9973 )
2020-08-25 13:22:25 +02:00
raoul-khour-ts
c8c4832794
Prevent Local Worker creation from blocking remote worker creation by creating remote workers before local worker ( #10245 )
...
* create remote workers before local worker
* reformatted
2020-08-24 12:29:55 -07:00
Michael Luo
48a39d7cb9
[RLlib] Deepmind Control Suite Examples ( #9751 )
2020-08-23 12:53:08 +02:00
krfricke
c31876002d
[tune/rllib] made wandb compatible with rllib trainables ( #10252 )
2020-08-21 17:25:52 -07:00
Sven Mika
e968b52cb7
[RLlib] Trajectory view API - 03 Fast LSTM + prev actions/rewards ( #9950 )
2020-08-21 12:35:16 +02:00
Sven Mika
d14b501692
[RLlib] First attempt at cleaning up algo code in RLlib: PG. ( #10115 )
2020-08-20 17:05:57 +02:00
Raphael Avalos
8b704eb419
Small fix for Cuda Torch DQN. ( #10177 )
2020-08-19 13:28:05 -07:00
Sven Mika
2cbe29a7fa
[RLlib] Curiosity minor fixes, do-overs, and testing. ( #10143 )
2020-08-19 17:49:50 +02:00
Tomasz Wrona
aff7f19360
[tune] Added logger_config field ( #8521 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2020-08-18 11:10:22 -07:00
Eric Liang
ca133e2699
[rllib] Remove extra model config kwargs passed incorrectly for Torch models ( #10055 )
2020-08-17 11:12:20 -07:00
Julius Frost
dc659ae89a
make action probabilities a numpy array ( #10122 )
2020-08-16 11:25:12 -07:00
Olli Huotari
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 Mika
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 Mika
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
Chua Cheow Huan
ea51e94729
[rllib] Learning rate schedule for DDPPO. ( #10006 )
...
* Get shared metrics, increment counter & set global vars for remote workers.
* Add unit test to test lr_schedule for DDPPO.
* Broadcast the local set of global vars to remote workers instead of independently setting the global vars on each rollout worker.
2020-08-15 00:51:45 -07:00
Tanay Wakhare
1826b29757
[RLlib] Curiosity (intrinsic motivation) Exploration module. ( #9912 )
2020-08-13 20:14:16 +02:00
Sven Mika
66d204e078
[RLlib] Model documentation enhancements. ( #10011 )
2020-08-13 13:36:40 +02:00
Sven Mika
0effcda3e4
Add missing int-casts for all shape calculating code (using np.product([some shape])). ( #10092 )
2020-08-13 12:04:22 +02:00
Julius Frost
6d9d2b320a
[RLlib] Support windows drives other than C drive for the offline json API ( #9909 )
2020-08-13 11:57:54 +02:00
