Semi-Supervised Apprenticeship Learning

Abstract : In apprenticeship learning we aim to learn a good policy by observing the behavior of an expert or a set of experts. In particular, we consider the case where the expert acts so as to maximize an unknown reward function defined as a linear combination of a set of state features. In this paper, we consider the setting where we observe many sample trajectories (i.e., sequences of states) but only one or a few of them are labeled as experts' trajectories. We investigate the conditions under which the remaining unlabeled trajectories can help in learning a policy with a good performance. In particular, we define an extension to the max-margin inverse reinforcement learning proposed by Abbeel and Ng (2004) where, at each iteration, the max-margin optimization step is replaced by a semi-supervised optimization problem which favors classifiers separating clusters of trajectories. Finally, we report empirical results on two grid-world domains showing that the semi-supervised algorithm is able to output a better policy in fewer iterations than the related algorithm that does not take the unlabeled trajectories into account.
Document type :
Conference papers
Marc Peter Deisenroth and Csaba Szepesvári and Jan Peters. he 10th European Workshop on Reinforcement Learning (EWRL 2012), Jun 2012, Edinburgh, United Kingdom. Sparc, 24, pp.131-141, 2012, The 10th European Workshop on Reinforcement Learning


https://hal.inria.fr/hal-00747921
Contributor : Michal Valko <>
Submitted on : Wednesday, January 16, 2013 - 3:21:17 PM
Last modification on : Friday, July 12, 2013 - 1:20:25 PM

File

valko2012semi-supervised_publi...
fileSource_public_greenPublisher

Identifiers

  • HAL Id : hal-00747921, version 2

Collections

Citation

Michal Valko, Mohammad Ghavamzadeh, Alessandro Lazaric. Semi-Supervised Apprenticeship Learning. Marc Peter Deisenroth and Csaba Szepesvári and Jan Peters. he 10th European Workshop on Reinforcement Learning (EWRL 2012), Jun 2012, Edinburgh, United Kingdom. Sparc, 24, pp.131-141, 2012, The 10th European Workshop on Reinforcement Learning. <hal-00747921v2>

Export

Share

Metrics

Consultation de
la notice

101

Téléchargement du document

48