[bug-fix] Fix stats reporting for reward signals in SAC

[ervteng]

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)

• Bug fix
• New feature
• Code refactor
• Breaking change
• Documentation update
• Other (please describe)

Checklist

• Added tests that prove my fix is effective or that my feature works
• Updated the changelog (if applicable)
• Updated the documentation (if applicable)
• Updated the migration guide (if applicable)

Other comments

[andrewcoh]

LGTM