---
title: "Direct Policy Iteration with Demonstrations"
authors:
  - "Jessica Chemali"
  - "Alessandro Lazaric"
doi: ""
url: "https://ijcai.org/proceedings/2015/476"
pdf: "https://ijcai.org/proceedings/2015/0476.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "3380-3385"
track: "Special Track on Machine Learning"
keywords:
---

# Direct Policy Iteration with Demonstrations

Jessica Chemali, Alessandro Lazaric

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 3380-3385.

## 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.