Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions
Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions
Ronald J. Williams and Leemon C. Baird III, 1994
Download
Abstract
(unavailable)
BibTeX Entry
@InProceedings{Williams+Baird:1994, author = "Williams, Ronald J. and Baird III, Leemon C.", title = "Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions", booktitle = "Proceedings of the Tenth Yale Workshop on Adaptive and Learning Systems", year = "1994", publisher = "Center for Systems Science, Yale University", address = "New Haven, CT, USA", url = "http://leemon.com/papers/1994wb.pdf", bib2html_rescat = "Function Approximation", }