[bug-fix] Fix stats reporting for reward signals in SAC #3606
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Outdated suggestions cannot be applied.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.
Proposed change(s)
When the Optimizer was split from the Policy, SAC was still using the Policy's reward signals to write the reward values to Tensorboard. This meant that the Policy's reward stats (e.g. Extrinsic Reward, GAIL Reward) was always 0.
This PR fixes the bug and removes the unnecessary reward_signals dict in Policy.
Types of change(s)
Checklist
Other comments