Linsey Pang

S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic

Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity and robustness. Notably, in Maximum Entropy reinforcement learning (MaxEnt RL), the policy is modeled as an expressive energy-based model (EBM) over the Q-values. Ho…