Learning to select goals in Automated Planning with Deep-Q Learning

Carlos Núñez-Molina, Juan Fernández-Olivares, Raúl Pérez

Abstract: Highlights•Deep Q-Learning is used by a planning agent to learn to select subgoals.•Our approach reduces planning time in online execution.•Our approach generalizes better than standard Deep Q-Learning.•Our approach is more sample-efficient than standard Deep Q-Learning.