---
title: "Approximate Policy Iteration using Large-Margin Classifiers"
authors:
  - "Michail G. Lagoudakis"
  - "Ronald Parr"
doi: ""
url: "https://ijcai.org/proceedings/2003/226"
pdf: "https://ijcai.org/proceedings/2003/0226.pdf"
venue: "Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence"
year: 2003
pages: "1432-1433"
track: ""
keywords:
---

# Approximate Policy Iteration using Large-Margin Classifiers

Michail G. Lagoudakis, Ronald Parr

*Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence*, pages 1432-1433.

## Abstract

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.