A learning algorithm for risk-sensitive cost
Document Type
Article
Publication Title
Mathematics of Operations Research
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 Date
1-4-2008
Publisher
Informs
Volume
Vol.33
Issue
Iss.4
Recommended Citation
Basu, Arnab; Bhattacharyya, Tirthankar; and Borkar, Vivek S, "A learning algorithm for risk-sensitive cost" (2008). Faculty Publications. 943.
https://research.iimb.ac.in/fac_pubs/943
COinS
