Variance Reduction for Evolution Strategies via Structured Control Variates

CoRR, pp. 646-656, 2019.

Cited by: 3|Views25
EI

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments