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.

Authors

• Michail G. Lagoudakis Duke University; Michael L. Littman
• Ronald Parr

Keywords

No keywords are indexed for this paper.