Commit graph

116 commits

Author SHA1 Message Date
Sven Mika
2ccf08ad10
[RLlib] Bug fix: DQN goes into negative epsilon values after reaching explora… (#6971)
* Bug fix: DQN goes into negative epsilon values after reaching exploration percentage.

* Add `epsilon_initial_eps` to SAC to pass test_nested_spaces.py.

* Add `exploration_initial_eps` to QMIX default config.
2020-01-31 09:54:12 -08:00
Sven Mika
303547f119 [RLlib] Policy-classes cleanup and torch/tf unification. (#6770) 2020-01-17 22:26:28 -08:00
Sven Mika
e6227082bd [RLlib] Add torch flag to train.py (#6807) 2020-01-17 18:48:44 -08:00
Sven Mika
2bcf72e306 DQN distributional model: Replace all legacy tf.contrib imports with tf.keras.layers.xyz or tf.initializers.xyz. (#6772)
- This fixes a test case in test_evaluators.py.
2020-01-13 21:48:16 -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
Zhongxia Yan
98689bd263 Changed foreach_policy to foreach_trainable_policy (#6564)
Changed foreach_policy to foreach_trainable_policy in DQN when disabling exploration. This makes it consistent with the rest of the file
2019-12-26 19:50:48 -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
cf90394a09
[rllib] Fix TF2 import of EagerVariableStore (#5625) 2019-09-07 12:10:03 -07:00
Eric Liang
19bbf1eb4d [rllib] Revert [rllib] Port DDPG to the build_tf_policy pattern (#5626) 2019-09-04 21:39:22 -07:00
Eric Liang
daf38c8723
[tune] Deprecate tune.function (#5601)
* remove tune function

* remove examples

* Update tune-usage.rst
2019-08-31 16:00:10 -07:00
gehring
b520f6141e [rllib] Adds eager support with a generic TFEagerPolicy class (#5436) 2019-08-23 14:21:11 +08:00
Eric Liang
a1d2e17623
[rllib] Autoregressive action distributions (#5304) 2019-08-10 14:05:12 -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