Scale-Adaptive Balancing of Exploration and Exploitation in Classical PlanningStephen WissowMasataro Asai2024ECAI 2024
On Using Admissible Bounds for Learning Forward Search HeuristicsCarlos Núñez-molinaMasataro Asaiet al.2024IJCAI 2024
Is Policy Learning Overrated?: Width-Based Planning and Active Learning for AtariBenjamin AytonMasataro Asai2022ICAPS 2022