Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning. (arXiv:2111.08066v3 [cs.LG] UPDATED)

Offline reinforcement learning -- learning a policy from a batch of data --
is known to be hard for general MDPs. These results motivate the need to look
at specific classes of MDPs where offline reinforcement learning might be
feasible. In this work, we explore a restricted class of MDPs to obtain
guarantees for offline reinforcement learning. The key property, which we call
Action Impact Regularity (AIR), is that actions primarily impact a part of the
state (an endogenous component) …

arxiv exogenous impact learning lg reinforcement reinforcement learning state variables