{"type":"ScholarlyArticle","title":"Approximate Policy Iteration using Large-Margin Classifiers","authors":[{"name":"Michail G. Lagoudakis","slug":"michail-g-lagoudakis","given":"Michail G.","family":"Lagoudakis","affiliation":""},{"name":"Ronald Parr","slug":"ronald-parr","given":"Ronald","family":"Parr","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2003/226","pdf":"https://ijcai.org/proceedings/2003/0226.pdf","markdown":"https://ijcai.org/proceedings/2003/226.md","bibtex":"https://ijcai.org/proceedings/2003/bibtex/226","volume":{"slug":"2003","title":"Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2003","url":"https://ijcai.org/proceedings/2003/","year":2003,"location":"Acapulco, Mexico","dates":"","editors":"Georg Gottlob","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":226,"pages":{"first":1432,"last":1433},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}