Variance Reduction for Evolution Strategies via Structured Control Variates
CoRR, pp. 646-656, 2019.
Evolution Strategies (ES) are a powerful class of blackbox optimization techniques that recently became a competitive alternative to state-of-the-art policy gradient (PG) algorithms for reinforcement learning (RL). We propose a new method for improving accuracy of the ES algorithms, that as opposed to recent approaches utilizing only Mo...More
PPT (Upload PPT)