# Answer Set Programming for Non-Stationary Markov Decision Processes

## TL;DR

This paper introduces ASP(RL), a novel method combining Answer Set Programming and Reinforcement Learning to efficiently find optimal policies in non-stationary Markov Decision Processes, addressing challenges of unforeseen domain changes.

## Contribution

The paper presents ASP(RL), a new approach integrating ASP and RL to handle non-stationary domains in MDPs, which was not previously explored.

## Key findings

- ASP(RL) efficiently finds optimal solutions in non-stationary MDPs.
- The method effectively adapts to unforeseen changes in the domain.
- Results demonstrate improved performance over traditional RL methods.

## Abstract

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.