Provably Robust Blackbox Optimization for Reinforcement Learning

Understand

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics.

• However, it is well known that DFO methods suffer from prohibitively high sampling complexity.
• They can also be very sensitive to noisy rewards and stochastic dynamics.
• In this paper, we propose a new class of algorithms, called Robust Blackbox Optimization (RBO).