55 search results - page 4 / 11 » Approximate Policy Iteration using Large-Margin Classifiers |
AAAI
2006
13 years 6 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
NIPS
2000
13 years 6 months ago
2000
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...
ATAL
2009
Springer
13 years 12 months ago
2009
Springer
One of the key problems in reinforcement learning is balancing exploration and exploitation. Another is learning and acting in large or even continuous Markov decision processes (...
ICANN
2007
Springer
13 years 9 months ago
2007
Springer
Abstract. Trained support vector machines (SVMs) have a slow runtime classification speed if the classification problem is noisy and the sample data set is large. Approximating the...
CORR
2010
Springer
13 years 5 months ago
2010
Springer
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...