Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning. (arXiv:2205.12184v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2205.12184

Continuous-time reinforcement learning offers an appealing formalism for
describing control problems in which the passage of time is not naturally
divided into discrete increments. Here we consider the problem of predicting
the distribution of returns obtained by an agent interacting in a
continuous-time, stochastic environment. Accurate return predictions have
proven useful for determining optimal policies for risk-sensitive control,
learning state representations, multiagent coordination, and more. We begin by
establishing the distributional analogue of the Hamilton-Jacobi-Bellman (HJB)
equation for It\^o diffusions …

arxiv learning lg reinforcement reinforcement learning time