ray/rllib/policy
Sven Mika 2fb219a658
[Ray RLlib] Fix tree import (#7662)
* Rollback.

* Fix import tree error by adding meaningful error and replacing by tf.nest wherever possible.

* LINT.

* LINT.

* Fix.

* Fix log-likelihood test case failing on travis.
2020-03-22 13:51:24 -07:00
..
tests [Ray RLlib] Fix tree import (#7662) 2020-03-22 13:51:24 -07:00
__init__.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
dynamic_tf_policy.py [rllib] Make timestep a required arg for exploration classes (#7380) 2020-03-04 13:00:37 -08:00
eager_tf_policy.py [Ray RLlib] Fix tree import (#7662) 2020-03-22 13:51:24 -07:00
policy.py [rllib] Fix per-worker exploration in Ape-X; make more kwargs required for future safety (#7504) 2020-03-10 11:14:14 -07:00
rnn_sequencing.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
sample_batch.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
tf_policy.py [Ray RLlib] Fix tree import (#7662) 2020-03-22 13:51:24 -07:00
tf_policy_template.py [RLlib] Policy.compute_log_likelihoods() and SAC refactor. (issue #7107) (#7124) 2020-02-22 14:19:49 -08:00
torch_policy.py [rllib] Fix per-worker exploration in Ape-X; make more kwargs required for future safety (#7504) 2020-03-10 11:14:14 -07:00
torch_policy_template.py [RLlib] Issue 7421: can't convert cuda tensor to numpy in torch ppo. (#7445) 2020-03-06 12:45:30 -08:00