Inverse Reinforcement Learning through Structured Classification - IMS - Equipe Information, Multimodalité et Signal Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Inverse Reinforcement Learning through Structured Classification

Résumé

This paper adresses the inverse reinforcement learning (IRL) problem, that is inferring a reward for which a demonstrated expert behavior is optimal. We introduce a new algorithm, SCIRL, whose principle is to use the so-called feature expectation of the expert as the parameterization of the score function of a multi-class classifier. This approach produces a reward function for which the expert policy is provably near-optimal. Contrary to most of existing IRL algorithms, SCIRL does not require solving the direct RL problem. Moreover, with an appropriate heuristic, it can succeed with only trajectories sampled according to the expert behavior. This is illustrated on a car driving simulator.
Fichier principal
Vignette du fichier
NIPS2012_0491.pdf (155.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00778624 , version 1 (21-01-2013)

Identifiants

  • HAL Id : hal-00778624 , version 1

Citer

Edouard Klein, Matthieu Geist, Bilal Piot, Olivier Pietquin. Inverse Reinforcement Learning through Structured Classification. NIPS 2012, Dec 2012, Lake Tahoe, Nevada, United States. pp.1-9. ⟨hal-00778624⟩
5986 Consultations
634 Téléchargements

Partager

Gmail Facebook X LinkedIn More