29 search results - page 6 / 6 » Linear Program Approximations for Factored Continuous-State ... |
AAAI
2010
13 years 6 months ago
2010
Partially-observable Markov decision processes (POMDPs) provide a powerful model for sequential decision-making problems with partially-observed state and are known to have (appro...
FOCS
2007
IEEE
13 years 11 months ago
2007
IEEE
d Abstract) Kousha Etessami LFCS, School of Informatics University of Edinburgh Mihalis Yannakakis Department of Computer Science Columbia University We reexamine what it means to...
CORR
2006
Springer
13 years 4 months ago
2006
Springer
This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...
IJCAI
2003
13 years 6 months ago
2003
A longstanding goal in planning research is the ability to generalize plans developed for some set of environments to a new but similar environment, with minimal or no replanning....