Compatible Reward Inverse Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Compatible Reward Inverse Reinforcement Learning

Résumé

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.
Fichier principal
Vignette du fichier
6800-compatible-reward-inverse-reinforcement-learning.pdf (452.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01653328 , version 1 (01-12-2017)

Identifiants

  • HAL Id : hal-01653328 , version 1

Citer

Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli. Compatible Reward Inverse Reinforcement Learning. The Thirty-first Annual Conference on Neural Information Processing Systems - NIPS 2017, Dec 2017, Long Beach, United States. ⟨hal-01653328⟩
209 Consultations
247 Téléchargements

Partager

Gmail Facebook X LinkedIn More