[rllib] Support batch norm layers#3369
Conversation
|
Test FAILed. |
|
Test FAILed. |
|
Test FAILed. |
|
Test FAILed. |
|
Ping @richardliaw |
|
Test FAILed. |
| if self._prev_reward_input is not None and prev_reward_batch: | ||
| builder.add_feed_dict({self._prev_reward_input: prev_reward_batch}) | ||
| builder.add_feed_dict({self._is_training: is_training}) | ||
| builder.add_feed_dict({self._is_training: False}) |
There was a problem hiding this comment.
where in the code is _is_training True?
There was a problem hiding this comment.
Co-Authored-By: ericl <ekhliang@gmail.com>
|
Test FAILed. |
|
Test FAILed. |
What do these changes do?
is_trainingtensor tobuild_layers_v2test_batch_norm.pyI don't think this will work for e.g., A3C which applies gradient updates separately, but it should work fine in the other execution modes.
Related issue number
Closes: #2023