28 search results - page 1 / 6 » Policy Improvement for POMDPs Using Normalized Importance Sa... |
UAI
2001
13 years 6 months ago
2001
We present a new method for estimating the expected return of a POMDP from experience. The estimator does not assume any knowledge of the POMDP, can estimate the returns for finit...
AAAI
2006
13 years 6 months ago
2006
We present a new algorithm, called incremental least squares policy iteration (ILSPI), for finding the infinite-horizon stationary policy for partially observable Markov decision ...
ATAL
2006
Springer
13 years 8 months ago
2006
Springer
Developing scalable algorithms for solving partially observable Markov decision processes (POMDPs) is an important challenge. One promising approach is based on representing POMDP...
AAAI
2008
13 years 7 months ago
2008
Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...
ATAL
2008
Springer
13 years 7 months ago
2008
Springer
Representing agent policies compactly is essential for improving the scalability of multi-agent planning algorithms. In this paper, we focus on developing a pruning technique that...