CONVERGENCE RATE OF LINEAR TWO-TIME-SCALE STOCHASTIC APPROXIMATION (2007)
Abstract. We study the rate of convergence of linear two-time-scale stochastic approximation methods. We consider two-time-scale linear iterations driven by i.i.d. noise, prove some results on their...
Convergence rate of linear two-time-scale stochastic approximation (2004)
Konda, Vijay R., Tsitsiklis, John N.
We study the rate of convergence of linear two-time-scale stochastic approximation methods. We consider two-time-scale linear iterations driven by i.i.d. noise, prove some results on their asymptotic...
Convergence rate of linear two-time-scale stochastic approximation (2004)
Konda, Vijay R., Tsitsiklis, John N.
We study the rate of convergence of linear two-time-scale stochastic approximation methods. We consider two-time-scale linear iterations driven by i.i.d. noise, prove some results on their asymptotic...
On De Finetti Coherence and Kolmogorov Probability (2004)
Vivek S. Borkar, Vijay R. Konda, Goldman Sachs, Sanjoy K. Mitter
This article addresses the problem of existence of a countably additive probability measure in the sense of Kolmogorov that is consistent with a probability assignment to a family of sets which is...
Tsitsiklis, “Linear Stochastic Approximation Driven by Slowly Varying (2003)
Vijay R. Konda, John N. Tsitsiklis
www.elsevier.com/locate/sysconle
Actor-critic algorithms (2000)
Abstract. In this paper, we propose and analyze a class of actor-critic algorithms. These are two-time-scale algorithms in which the critic uses temporal dierence (TD) learning with a linearly...
Actor-critic algorithms (2000)
Abstract. In this article, we propose and analyze a class of actor-critic algorithms. These are two-time-scale algorithms in which the critic uses temporal difference learning with a linearly...