Answer Set Programming for Non-Stationary Markov Decision Processes
This addresses the problem of sequential decision-making in dynamic environments for AI agents, but appears incremental as it integrates existing techniques.
The paper tackles the challenge of finding optimal policies in non-stationary domains with unforeseen changes by combining Markov Decision Processes and Reinforcement Learning with Answer Set Programming in a method called ASP(RL). Results indicate that ASP(RL) efficiently finds optimal solutions for MDPs representing such domains.
Non-stationary domains, where unforeseen changes happen, present a challenge for agents to find an optimal policy for a sequential decision making problem. This work investigates a solution to this problem that combines Markov Decision Processes (MDP) and Reinforcement Learning (RL) with Answer Set Programming (ASP) in a method we call ASP(RL). In this method, Answer Set Programming is used to find the possible trajectories of an MDP, from where Reinforcement Learning is applied to learn the optimal policy of the problem. Results show that ASP(RL) is capable of efficiently finding the optimal solution of an MDP representing non-stationary domains.