Commit graph

23 commits

Author SHA1 Message Date
AnanthHari
aa2a0cb6da Fixes empty state argument in compute_single_action method (#6894)
* Fixes empty `state` parameter in compute_single_action method

* Fixed style
2020-01-23 00:42:52 -08:00
Sven Mika
c957ed58ed [RLlib] Implement PPO torch version. (#6826) 2020-01-20 23:06:50 -08:00
Sven Mika
303547f119 [RLlib] Policy-classes cleanup and torch/tf unification. (#6770) 2020-01-17 22:26:28 -08:00
Sven
60d4d5e1aa Remove future imports (#6724)
* Remove all __future__ imports from RLlib.

* Remove (object) again from tf_run_builder.py::TFRunBuilder.

* Fix 2xLINT warnings.

* Fix broken appo_policy import (must be appo_tf_policy)

* Remove future imports from all other ray files (not just RLlib).

* Remove future imports from all other ray files (not just RLlib).

* Remove future import blocks that contain `unicode_literals` as well.
Revert appo_tf_policy.py to appo_policy.py (belongs to another PR).

* Add two empty lines before Schedule class.

* Put back __future__ imports into determine_tests_to_run.py. Fails otherwise on a py2/print related error.
2020-01-09 00:15:48 -08:00
Robert Nishihara
39a3459886 Remove (object) from class declarations. (#6658) 2020-01-02 17:42:13 -08:00
waldroje
e4c0843f60 Allow EntropyCoeffSchedule to accept custom schedule (#6158)
* modify tf_policy to enable EntropyCoeffSchedule to handle list, and avoid negative values under current implementation

* Update custom_metrics_and_callbacks.py

* Update tf_policy.py
2019-11-14 00:45:43 -08:00
Eric Liang
1f043daf69
[rllib] Fix and add test for LR annealing config 2019-11-07 12:17:27 -08:00
Eric Liang
16891e9379
[rllib] Don't use flat weights in non-eager mode (#6001) 2019-10-31 15:16:02 -07:00
Eric Liang
a0dcb45dc3
[rllib] Fix APEX priorities returning zero all the time (#5980)
* fix

* move example tests to end

* level err

* guard against none

* no trace test

* ignore thumbs

* np

* fix multi node

* fix
2019-10-26 13:23:42 -07:00
Eric Liang
f7bda0abad
[rllib] Fix rnn shape with multi-dimensional data (#5939)
* fix shape

* add test

* Update rnn_sequencing.py
2019-10-22 11:07:26 -07:00
Matthew A. Wright
0110941de5 rllib: use pytorch's fn to see if gpu is available (#5890) 2019-10-12 00:13:00 -07:00
Eric Liang
04e997fe0d
Fix TF2 / rllib test (#5846) 2019-10-07 14:25:16 -07:00
Eric Liang
c6919d315d
[rllib] Remove TorchPolicy locks (#5764)
* remove torch lock

* remove lock
2019-09-24 17:52:16 -07:00
gehring
8903bcd0c3 [rllib] Tracing for eager tensorflow policies with tf.function (#5705)
* Added tracing of eager policies with `tf.function`

* lint

* add config option

* add docs

* wip

* tracing now works with a3c

* typo

* none

* file doc

* returns

* syntax error

* syntax error
2019-09-17 01:44:20 -07:00
Eric Liang
bc6a95deb0
[rllib] Eager execution for centralized critic example, fix simple optimizer for multiagent (#5683) 2019-09-11 12:15:34 -07:00
Eric Liang
74abeab057
[rllib] Improve accessing model state docs (#5656)
* [rllib] better model docs

* fix

* s
2019-09-08 23:01:26 -07:00
Eric Liang
03a1b75852
[rllib] Fix some eager execution regressions with 1.13 (#5537)
* fix bugs with 1.13

* allow disable
2019-08-26 23:23:35 -07:00
gehring
b520f6141e [rllib] Adds eager support with a generic TFEagerPolicy class (#5436) 2019-08-23 14:21:11 +08:00
Eric Liang
79949fb8a0
[rllib] RLlib in 60 seconds documentation (#5430) 2019-08-12 17:39:02 -07:00
Eric Liang
a1d2e17623
[rllib] Autoregressive action distributions (#5304) 2019-08-10 14:05:12 -07:00
Eric Liang
592f313210
[rllib] Centralized critic / PPO example on TwoStepGame (#5392) 2019-08-08 14:03:28 -07:00
Matthew A. Wright
e3c9f7e83a Custom action distributions (#5164)
* custom action dist wip

* Test case for custom action dist

* ActionDistribution.get_parameter_shape_for_action_space pattern

* Edit exception message to also suggest using a custom action distribution

* Clean up ModelCatalog.get_action_dist

* Pass model config to ActionDistribution constructors

* Update custom action distribution test case

* Name fix

* Autoformatter

* parameter shape static methods for torch distributions

* Fix docstring

* Generalize fake array for graph initialization

* Fix action dist constructors

* Correct parameter shape static methods for multicategorical and gaussian

* Make suggested changes to custom action dist's

* Correct instances of not passing model config to action dist

* Autoformatter

* fix tuple distribution constructor

* bugfix
2019-08-06 11:13:16 -07:00
Eric Liang
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00