Goal Reasoning by Selecting Subgoals with Deep Q-Learning
This work addresses the problem of reducing planning time for online execution systems by offloading subgoal selection to a learned model, which is an incremental improvement for real-time AI systems.
This paper proposes a goal reasoning method that uses Deep Q-Learning to select subgoals, aiming to reduce planner load in time-constrained scenarios. The method, trained on a video game environment, significantly decreases planning time while maintaining plan quality compared to a satisfying planner.
In this work we propose a goal reasoning method which learns to select subgoals with Deep Q-Learning in order to decrease the load of a planner when faced with scenarios with tight time restrictions, such as online execution systems. We have designed a CNN-based goal selection module and trained it on a standard video game environment, testing it on different games (planning domains) and levels (planning problems) to measure its generalization abilities. When comparing its performance with a satisfying planner, the results obtained show both approaches are able to find plans of good quality, but our method greatly decreases planning time. We conclude our approach can be successfully applied to different types of domains (games), and shows good generalization properties when evaluated on new levels (problems) of the same game (domain).