Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes
Publication Date
2007
Journal or Book Title
JOURNAL OF MACHINE LEARNING RESEARCH
Pages
2169-2231
Volume
8
Recommended Citation
Mahadevan, S and Maggioni, M, "Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes" (2007). JOURNAL OF MACHINE LEARNING RESEARCH. 875.
Retrieved from https://scholarworks.umass.edu/cs_faculty_pubs/875
COinS