Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach

arXiv:2402.19265v1 Announce Type: cross
Abstract: Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling show great success to relax the computational demand and perform online planning. However, scaling to complex realistic domains with many actions and long planning horizons is still a major challenge, and a key point to achieve good performance is guiding the action-selection process …

abstract arxiv belief computational cs.ai cs.lg cs.lo decision demand distribution framework guidance inductive logic markov observable planning policy probability processes programming sampling show state success type uncertainty