Results 1  10
of
83,053
Hard Constrained SemiMarkov Decision Processes
"... In multiple criteria Markov Decision Processes (MDP) where multiple costs are incurred at every decision point, current methods solve them by minimising the expected primary cost criterion while constraining the expectations of other cost criteria to some critical values. However, systems are often ..."
Abstract
 Add to MetaCart
In multiple criteria Markov Decision Processes (MDP) where multiple costs are incurred at every decision point, current methods solve them by minimising the expected primary cost criterion while constraining the expectations of other cost criteria to some critical values. However, systems are of
Duality between Probability and Optimization
 In Proceedings of the workshop &quot;Idempotency
, 1997
"... this paper. The link between the weak convergence and the epigraph convergence used in convex analysis is done. The Cramer transform used in the large deviation literature is defined as the composition of the Laplace transform by the logarithm by the Fenchel transform. It transforms convolution into ..."
Abstract

Cited by 18 (7 self)
 Add to MetaCart
this paper. The link between the weak convergence and the epigraph convergence used in convex analysis is done. The Cramer transform used in the large deviation literature is defined as the composition of the Laplace transform by the logarithm by the Fenchel transform. It transforms convolution
Asymptotic Properties of Constrained Markov Decision Processes
, 1991
"... We present in this paper several asymptotic properties of constrained Markov Decision Processes (MDPs) with a countable state space. We treat both the discounted and the expected average cost, with unbounded cost. We are interested in (1) the convergence of finite horizon MDPs to the infinite horizo ..."
Abstract

Cited by 12 (6 self)
 Add to MetaCart
We present in this paper several asymptotic properties of constrained Markov Decision Processes (MDPs) with a countable state space. We treat both the discounted and the expected average cost, with unbounded cost. We are interested in (1) the convergence of finite horizon MDPs to the infinite
Bounds for Markov Decision Processes
, 2011
"... We consider the problem of producing lower bounds on the optimal costtogo function of a Markov decision problem. We present two approaches to this problem: one based on the methodology of approximate linear programming (ALP) and another based on the socalled martingale duality approach. We show t ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
We consider the problem of producing lower bounds on the optimal costtogo function of a Markov decision problem. We present two approaches to this problem: one based on the methodology of approximate linear programming (ALP) and another based on the socalled martingale duality approach. We show
Solving Uncertain Markov Decision Processes
 Carnegie Mellon University
, 2001
"... The authors consider the fundamental problem of nding good policies in uncertain models. It is demonstrated that although the general problem of nding the best policy with respect to the worst model is NPhard, in the special case of a convex uncertainty set the problem is tractable. A stochas ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
stochastic dynamic game is proposed, and the security equilibrium solution of the game is shown to correspond to the value function under the worst model and the optimal controller. The authors demonstrate that the uncertain model approach can be used to solve a class of nearly Markovian Decision
Integrating value functions and policy search for continuous Markov Decision Processes
"... Value function approaches for Markov decision processes have been used successfully to find optimal policies for a large number of problems. Recent findings have demonstrated that policy search can be used effectively in reinforcement learning when standard value function techniques become overwh ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Value function approaches for Markov decision processes have been used successfully to find optimal policies for a large number of problems. Recent findings have demonstrated that policy search can be used effectively in reinforcement learning when standard value function techniques become
Markov Decision Processes in Finance
, 2006
"... I am very grateful to my supervisor Dr Sandjai Bhulai from the Vrije Universiteit for his encouraging and inspiring supervision during my work with this masterâ€™s thesis. He was always available to offer his help to me. i This thesis presents the theory applicable to the option pricing and shortfall ..."
Abstract
 Add to MetaCart
fall risk minimization problem. The market is arbitragefree without transaction costs and the underlying asset price process is assumed to possess a Markov chain structure. Under these assumptions, stochastic dynamic programming is exploited to price the European type option. By using the utility concept
Denumerable Constrained Markov Decision Problems And Finite Approximations
, 1992
"... The purpose of this paper is two fold. First to establish the Theory of discounted constrained Markov Decision Processes with a countable state and action spaces with general multichain structure. Second, to introduce finite approximation methods. We define the occupation measures and obtain proper ..."
Abstract

Cited by 16 (8 self)
 Add to MetaCart
The purpose of this paper is two fold. First to establish the Theory of discounted constrained Markov Decision Processes with a countable state and action spaces with general multichain structure. Second, to introduce finite approximation methods. We define the occupation measures and obtain
Applying Markov Decision Process
, 2011
"... This paper deals with cognitive theories behind agentbased modeling of learning and information processing methodologies. Herein, I undertake a descriptive analysis of how human agents learn to select action and maximize their value function under reinforcement learning model. In doing so, I have c ..."
Abstract
 Add to MetaCart
considered the spatiotemporal environment under bounded rationality using Markov Decision process modeling to generalize patterns of agent behavior by analyzing the determinants of value functions, and of factors that modify policyactioninduced cognitive abilities. Since detecting patterns are central
Results 1  10
of
83,053