A new learning algorithm for optimal stopping

Borkar, Vivek S. ; Pinto, Jervis ; Prabhu, Tarun (2009) A new learning algorithm for optimal stopping Discrete Event Dynamic Systems: Theory and Applications, 19 (1). pp. 91-113. ISSN 0924-6703

Full text not available from this repository.

Official URL: http://www.springerlink.com/content/j2gg544w222725...

Related URL: http://dx.doi.org/10.1007/s10626-008-0055-2


A linear programming formulation of the optimal stopping problem for Markov decision processes is approximated using linear function approximation. Using this formulation, a reinforcement learning scheme based on a primal-dual method and incorporating a sampling device called 'split sampling'is proposed and analyzed. An illustrative example from option pricing is also included.

Item Type:Article
Source:Copyright of this article belongs to Springer-Verlag.
Keywords:Learning Algorithm; Optimal Stopping; Linear Programming; Primal-dual Methods; Split Sampling; Option Pricing
ID Code:5368
Deposited On:18 Oct 2010 09:01
Last Modified:20 May 2011 08:45

Repository Staff Only: item control page