This approach offers the possibility of a systematic and practical methodology for ad- dressing complex stochastic control problems. Despite the success of ...

We consider the solution to large stochastic control problems by means of methods that rely on compact representations and a vari(cid:173) ant of the value ...

We consider the solution to large stochastic control problems by means of methods that rely on compact representations and a vari-.

Stable linear approximations to dynamic programming for stochastic control problems with local transitions. Author(s). Van Roy, Benjamin.; Tsitsiklis, John N ...

We consider the solution to large stochastic control problems by means of methods that rely on compact representations and a vari- ant of the value ...

Benjamin Van Roy, John N. Tsitsiklis: Stable LInear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions.

First, we will cast function approximators as expansion or contrac- tion mappings; this distinction captures the essential difference between approximators that ...

We study an efficient method based on linear programming for approximating solutions to such problems.

Benjamin Van Roy and John Tsitsiklis, Stable Linear Approximations to Dynamic Programming for Stochastic Control Problems with Local Transitions, NeurIPS, 1996.

We propose and analyze an algorithm that approximates solutions to the problem of optimal stopping in a discounted irreducible aperiodic Markov chain.