SAC
E426679
UNEXPLORED
SAC (Soft Actor-Critic) is a popular off-policy deep reinforcement learning algorithm that optimizes both expected return and policy entropy to achieve stable and efficient learning in continuous control tasks.
Referenced by (2)
| Subject (surface form when different) | Predicate |
|---|---|
|
Stable Baselines
→
|
supportsAlgorithm |
|
TF-Agents
→
|
supportsAlgorithmFamily |