Work

Direct Policy Iteration with Demonstrations

Year: 2015

Type: conference-paper

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.

Source: LillOA (Université de Lille (University Of Lille))

Authors: Chemali, Jessica, Lazaric, Alessandro

Institutions: Carnegie Mellon University, Université de Lille, Centre de Recherche en Informatique, Signal et Automatique de Lille

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Agence Nationale de la Recherche, Ministère de l'Education Nationale, de l'Enseignement Superieur et de la Recherche

Award: Extraction and Transfer of Knowledge in Reinforcement Learning

OpenAlex ID: W2253157232

FWCI: 1.089

Cites: 17

Cited by: 26

Related to: 10