A learning algorithm for risk-sensitive cost

The Digital Institutional Repository of IIM Bangalore

Please use this identifier to cite or link to this item: https://repository.iimb.ac.in/handle/2074/10953

DC Field	Value	Language
dc.contributor.author	Basu, Arnab
dc.contributor.author	Bhattacharyya, Tirthankar
dc.contributor.author	Borkar, Vivek S
dc.date.accessioned	2020-03-23T09:25:11Z	-
dc.date.available	2020-03-23T09:25:11Z	-
dc.date.issued	2008
dc.identifier.issn	0364-765X
dc.identifier.uri	https://repository.iimb.ac.in/handle/2074/10953	-
dc.description.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.
dc.description.sponsorship	Infosys Fellowship; Universities Grants Commission, Government of India; J.C. Bose Fellowship of the Department of Science and Technology, Government of India
dc.publisher	Informs
dc.subject	Learning Algorithm
dc.subject	Risk-Sensitive Cost
dc.subject	Function Approximation
dc.subject	Stochastic Approximation
dc.title	A learning algorithm for risk-sensitive cost
dc.type	Journal Article
dc.identifier.doi	10.1287/moor.1080.0324
dc.pages	880-898p.
dc.vol.no	Vol.33	-
dc.issue.no	Iss.4	-
dc.journal.name	Mathematics of Operations Research
Appears in Collections:	2000-2009

Check