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.
Type de document :
Communication dans un congrès
IJCAI - 24th International Joint Conference on Artificial Intelligence, Jul 2015, Buenos Aires, Argentina. 2015
https://hal.inria.fr/hal-01237659
Contributeur : Alessandro Lazaric
<>
Soumis le : jeudi 3 décembre 2015 - 15:46:20
Dernière modification le : vendredi 22 mars 2019 - 01:35:27
Document(s) archivé(s) le : samedi 29 avril 2017 - 07:49:10
Jessica Chemali, Alessandro Lazaric. Direct Policy Iteration with Demonstrations. IJCAI - 24th International Joint Conference on Artificial Intelligence, Jul 2015, Buenos Aires, Argentina. 2015. 〈hal-01237659〉
