Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes.pdf
1.34MB
Type: Paper Tags: Bibtex:
@article{8:74,author={Sridhar Mahadevan and Mauro Maggioni}, Title={Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes},journal={Journal of Machine Learning Research},volume={8}, url={http://www.jmlr.org/papers/volume8/mahadevan07a/mahadevan07a.pdf}}
Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes.pdf