An efficient approach to model-based hierarchical reinforcement learning

• Main Authors: LI, Zhuoru, NARAYAN, Akshay, LEONG, Tze-Yun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Reinforcement learning; hierarchical reinforcement learning; MAXQ; R-MAX; model-based reinforcement learning; Bench-mark problems; Feature combination; Hierarchical reinforcement learning; Levels of abstraction; Model based approach; Problem characterization; Robotic environments; State-of-the-art algorithms; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/4398; https://ink.library.smu.edu.sg/context/sis_research/article/5401/viewcontent/14771_66644_1_PB.pdf
• Institution: Singapore Management University

We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the stateof-the-art algorithms, and scales well in very large problems.