Premium ContentSoft Actor-Critic (SAC)
Maximum-entropy RL
This chapter requires a subscription to access.
What you'll unlock:
- 1. The Maximum-Entropy Framework
- 2. SAC Derivation
- 3. Automatic Temperature Tuning
- 4. Discrete-Action SAC
- 5. Modern Variants: TQC, CrossQ, DroQ, REDQ
- 6. SAC on Humanoid
Subscribe to UnlockAlready have an account? Sign in