Learning Representation and Control in Markov Decision Processes
New Frontiers
Omschrijving
Describes methods for automatically compressing Markov decision processes (MDPs) by learning a low-dimensional linear approximation defined by an orthogonal set of basis functions. A unique feature of the text is the use of Laplacian operators, whose matrix representations have non-positive off-diagonal elements and zero row sums.
Ik heb een vraag over het boek: ‘Learning Representation and Control in Markov Decision Processes - Mahadaven, Sridhar’.
Vul het onderstaande formulier in.
We zullen zo spoedig mogelijk antwoorden.
