Learning Representation and Control in Continuous Markov Decision Processes

This paper presents a novel framework for simultaneously learning representation and control in continuous Markov decision processes. Our approach builds on the framework of proto-value functions, in which the underlying representation or basis functions are automatically derived from a spectral analysis of the state space manifold. The proto-value functions correspond to the eigenfunctions of the graph Laplacian. We describe an approach to extend the eigenfunctions to novel states using the Nystr

• Type: Conference
• Year: 2006
• Where: AAAI
• Authors: Sridhar Mahadevan, Mauro Maggioni, Kimberly Ferguson, Sarah Osentoski
• Keywords: AAAI 2006, Basis Function, Continuous Markov Decision, Intelligent Agents, Proto-value Functions