Compatible Reward Inverse Reinforcement Learning

Metelli, Alberto; Pirotta, Matteo; Restelli, Marcello

Type de document :

Communication dans un congrès avec actes

Titre :

Compatible Reward Inverse Reinforcement Learning

Auteur(s) :

Metelli, Alberto [Auteur]
Department of Electronics, Information, and Bioengineering [Milano] [DEIB]
Pirotta, Matteo [Auteur]
Sequential Learning [SEQUEL]
Restelli, Marcello [Auteur]
Department of Electronics, Information, and Bioengineering [Milano] [DEIB]

Titre de la manifestation scientifique :

The Thirty-first Annual Conference on Neural Information Processing Systems - NIPS 2017

Ville :

Long Beach

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2017-12-04

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

Inverse Reinforcement Learning (IRL) is an effective approach to recover a reward function that explains the behavior of an expert by observing a set of demonstrations. This paper is about a novel model-free IRL approach ...
Lire la suite >Inverse Reinforcement Learning (IRL) is an effective approach to recover a reward function that explains the behavior of an expert by observing a set of demonstrations. This paper is about a novel model-free IRL approach that, differently from most of the existing IRL algorithms, does not require to specify a function space where to search for the expert's reward function. Leveraging on the fact that the policy gradient needs to be zero for any optimal policy, the algorithm generates a set of basis functions that span the subspace of reward functions that make the policy gradient vanish. Within this subspace, using a second-order criterion, we search for the reward function that penalizes the most a deviation from the expert's policy. After introducing our approach for finite domains, we extend it to continuous ones. The proposed approach is empirically compared to other IRL methods both in the (finite) Taxi domain and in the (continuous) Linear Quadratic Gaussian (LQG) and Car on the Hill environments.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

https://hal.inria.fr/hal-01653328/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-01653328/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-01653328/document
Accès libre
Accéder au document

document
Accès libre
Accéder au document

6800-compatible-reward-inverse-reinforcement-learning.pdf
Accès libre
Accéder au document

document
Accès libre
Accéder au document

6800-compatible-reward-inverse-reinforcement-learning.pdf
Accès libre
Accéder au document

Compatible Reward Inverse Reinforcement Learning BibTeX CSV Excel RIS

Fichiers

Compatible Reward Inverse Reinforcement Learning

BibTeX

CSV

Excel

RIS