Online feature selection for model-based reinforcement learning

• المؤلفون الرئيسيون: Nguyen, Trung Thanh, Li, Zhuoru, Silander, Tomi, Tze-Yun LEONG
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2013
• الموضوعات: Artificial intelligence; Software engineering High dimensional spaces; Learning techniques; Model-based reinforcement learning; Online feature selection; Relevant features; Theoretical guarantees; Transition model; World dynamics; Databases and Information Systems
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/3030

We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition...