QUOTA: The Quantile Option Architecture for Reinforcement Learning

  • Shangtong Zhang University of Alberta
  • Hengshuai Yao Huawei Technologies

Abstract

In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators.

Published
2019-07-17
Section
AAAI Technical Track: Machine Learning