A learning algorithm for risk-sensitive cost

Basu, Arnab ; Bhattacharyya, Tirthankar ; Borkar, Vivek S. (2008) A learning algorithm for risk-sensitive cost Mathematics of Operations Research, 33 (4). pp. 880-898. ISSN 0364-765X

Full text not available from this repository.

Official URL: http://mor.journal.informs.org/content/33/4/880.sh...

Related URL: http://dx.doi.org/10.1287/moor.1080.0324


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.

Item Type:Article
Source:Copyright of this article belongs to INFORMS.
Keywords:Learning Algorithm; Risk-Sensitive Cost; Function Approximation; Stochastic Approximation
ID Code:81468
Deposited On:07 Feb 2012 04:55
Last Modified:07 Feb 2012 04:55

Repository Staff Only: item control page