Publication View

A Learning Algorithm for Risk-Sensitive Cost (2008)

Abstract
A linear function approximation-based reinforcement learning algorithm is proposed for Markov decision processes with infinite horizon risk-sensitive cost. Its convergence is proved using the "o.d.e. method" for stochastic approximation. The scheme is also extended to continuous state space processes.

Publication details
Download http://eprints.iisc.ernet.in/17471/1/fulltext.pdf
Publisher Informs
Repository ePrints@iisc (India)
Keywords Mathematics
Type Journal Article, PeerReviewed
Relation http://mor.journal.informs.org/cgi/content/abstract/33/4/880
http://eprints.iisc.ernet.in/17471/