Markov Decision Processes with Unknown State Feature Values for Safe Exploration using Gaussian Processes

[BLD+20] Matthew Budd, Bruno Lacerda, Paul Duckworth, Andrew West, Barry Lennox and Nick Hawes. Markov Decision Processes with Unknown State Feature Values for Safe Exploration using Gaussian Processes. In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'20). 2020. [Presents techniques for safe planning that combine MDPs and Gaussian processes, building on PRISM as a backend solver.]

Search for this paper
Google · Google Scholar