{"type":"ScholarlyArticle","title":"Direct Policy Iteration with Demonstrations","authors":[{"name":"Jessica Chemali","slug":"jessica-chemali","given":"Jessica","family":"Chemali","affiliation":""},{"name":"Alessandro Lazaric","slug":"alessandro-lazaric","given":"Alessandro","family":"Lazaric","affiliation":""}],"abstract":"We consider the problem of learning the optimal policy of an unknown Markov decision process (MDP) when expert demonstrations are available along with interaction samples. We build on classification-based policy iteration to perform a seamless integration of interaction and expert data, thus obtaining an algorithm which can benefit from both sources of information at the same time. Furthermore, we provide a full theoretical analysis of the performance across iterations providing insights on how the algorithm works. Finally, we report an empirical evaluation of the algorithm and a comparison with the state-of-the-art algorithms.","doi":null,"url":"https://ijcai.org/proceedings/2015/476","pdf":"https://ijcai.org/proceedings/2015/0476.pdf","markdown":"https://ijcai.org/proceedings/2015/476.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/476","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Special Track on Machine Learning","track":"Special Track on Machine Learning","number":476,"pages":{"first":3380,"last":3385},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}