QUOTA: The Quantile Option Architecture for Reinforcement Learning
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 …