# Distributional Reinforcement Learning with Quantile Regression

27 Oct 2017Will DabneyMark RowlandMarc G. BellemareRémi Munos

In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the observed long-term return... (read more)

PDF Abstract