{"pk":49197,"title":"Mental Model Alignment: Building Cognitive Interfaces for Explainable Reinforcement Learning","subtitle":null,"abstract":"Deep reinforcement learning has achieved remarkable success in complex decision-making tasks, yet its black-box nature limits practical deployment in safety-critical domains. Current explainable reinforcement learning methods often fail to align with the hierarchical and temporal structure of human mental models, which are central to cognitive science theories of decision making. To bridge this gap, we propose Mental Model Alignment (MMA), a novel framework that constructs cognitive interfaces using behavior trees to harmonize AI decision-making with human-understandable reasoning. MMA introduces three innovations: (1) a mental model encoder that captures the hierarchical decomposition of tasks into subgoals, mirroring human cognitive processes; (2) a cognitive pruning algorithm that simplifies BTs while preserving decision-critical nodes aligned with human mental schemas; and (3) a mental effort metric to quantify the cognitive load required for users to interpret policies. Evaluated across six benchmark environments, MMA outperforms state-of-the-art methods in interpretability, policy fidelity, and computational efficiency. Our results demonstrate that aligning AI policies with human mental models significantly enhances trust and usability in real-world applications.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Papers with Oral Presentation","is_remote":true,"remote_url":"https://escholarship.org/uc/item/7gj6t809","frozenauthors":[{"first_name":"Kejia","middle_name":"","last_name":"Wan","name_suffix":"","institution":"National University of Defense Technology","department":""},{"first_name":"Yuntao","middle_name":"","last_name":"Liu","name_suffix":"","institution":"Academy of Military Science, Beijing, China","department":""},{"first_name":"Hengzhu","middle_name":"","last_name":"Liu","name_suffix":"","institution":"National University of Defense Technology","department":""},{"first_name":"Xinhai","middle_name":"","last_name":"Xu","name_suffix":"","institution":"Academy of Military Science","department":""},{"first_name":"Hao","middle_name":"","last_name":"Tang","name_suffix":"","institution":"NUDT","department":""},{"first_name":"Jinlong","middle_name":"","last_name":"Tian","name_suffix":"","institution":"National University of Defense Technology","department":""},{"first_name":"Xianglong","middle_name":"","last_name":"Li","name_suffix":"","institution":"Academy of Military Sciences","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2025-01-01T19:00:00+01:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/49197/galley/37158/download/"},{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/49197/galley/38703/download/"}]}