[Feature] Single call to value network in advantages #1256
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
Comment on lines
+1118
to
+1145
| # kwargs = {} | ||
| # if self.is_stateless and params is None: | ||
| # raise RuntimeError( | ||
| # "Expected params to be passed to advantage module but got none." | ||
| # ) | ||
| # if params is not None: | ||
| # kwargs["params"] = params | ||
| # | ||
| # if self.value_network is not None: | ||
| # with hold_out_net(self.value_network): | ||
| # # we may still need to pass gradient, but we don't want to assign grads to | ||
| # # value net params | ||
| # self.value_network(tensordict, **kwargs) | ||
| # | ||
| # value = tensordict.get(self.tensor_keys.value) | ||
| # | ||
| # step_td = step_mdp(tensordict) | ||
| # if target_params is not None: | ||
| # # we assume that target parameters are not differentiable | ||
| # kwargs["params"] = target_params | ||
| # elif "params" in kwargs: | ||
| # kwargs["params"] = kwargs["params"].detach() | ||
| # if self.value_network is not None: | ||
| # with hold_out_net(self.value_network): | ||
| # # we may still need to pass gradient, but we don't want to assign grads to | ||
| # # value net params | ||
| # self.value_network(step_td, **kwargs) | ||
| # next_value = step_td.get(self.tensor_keys.value) |
There was a problem hiding this comment.
Is the commented-out code left on purpose?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR allows advantages to call once and only once the value model.
If
adv.shiftedis set toTrueand if the params attandt+1match, the value net is called only once.In all other cases, vmap is used to batch the calls to the value net.
cc @tcbegley @apbard