Basu, Arnab and Bhattacharyya, Tirthankar and Borkar, Vivek S (2008) A Learning Algorithm for Risk-Sensitive Cost. In: Mathematics of Operations Research, 33 (4). pp. 880-898.
fulltext.pdf - Published Version
Restricted to Registered users only
Download (245Kb) | Request a copy
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:||Journal Article|
|Additional Information:||Copyright of this article belongs to Informs.|
|Keywords:||learning algorithm;risk-sensitive cost;function approximation;stochastic approximation.|
|Department/Centre:||Division of Physical & Mathematical Sciences > Mathematics|
|Date Deposited:||21 Jul 2009 07:43|
|Last Modified:||19 Sep 2010 04:57|
Actions (login required)