2 search results - page 1 / 1 » Decision Tree Methods for Finding Reusable MDP Homomorphisms |
AAAI
2006
13 years 6 months ago
2006
straction is a useful tool for agents interacting with environments. Good state abstractions are compact, reuseable, and easy to learn from sample data. This paper and extends two...
JMLR
2008
13 years 5 months ago
2008
In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...