Sciweavers

IJCAI
2003

Approximate Policy Iteration using Large-Margin Classifiers

13 years 5 months ago
Approximate Policy Iteration using Large-Margin Classifiers
We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to generalize and learn the improved policy over the entire state space. Using a multiclass support vector machine as the classifier, we obtained successful results on the inverted pendulum and the bicycle balancing and riding domains.
Michail G. Lagoudakis, Ronald Parr
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where IJCAI
Authors Michail G. Lagoudakis, Ronald Parr
Comments (0)