QUOTA: The Quantile Option Architecture for Reinforcement Learning

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.

Authors

• Shangtong Zhang University of Virginia, Charlottesville
• Hengshuai Yao Department of Computing Science, University of Alberta, Edmonton, Canada

Keywords

No keywords are indexed for this paper.