International audienceWe study the convergence of Markov decision processes, composed of a large number of objects, to optimization problems on ordinary differential equations. We show that the optimal reward of such a Markov decision process, which satisfies a Bellman equation, converges to the solution of a continuous Hamilton-Jacobi-Bellman (HJB) equation based on the mean field approximation of the Markov decision process. We give bounds on the difference of the rewards and an algorithm for deriving an approximating solution to the Markov decision process from a solution of the HJB equations. We illustrate the method on three examples pertaining, respectively, to investment strategies, population dynamics control and scheduling in queue...
Conclusion Motivation, description of the problem A Markov Decision Process We consider: System of N...
International audienceThis paper investigates the limit behavior of Markov decision processes made o...
We formally verify executable algorithms for solving Markov decision processes (MDPs) in the interac...
International audienceWe study the convergence of Markov decision processes, composed of a large num...
Abstract—We study the convergence of Markov decision pro-cesses, composed of a large number of objec...
We study the convergence of Markov decision processes, composed of a large number of objects, to opt...
We consider a finite number of $N$ statistically equal individuals, each moving on a finite set of s...
Abstract. State-based systems with discrete or continuous time are of-ten modelled with the help of ...
This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent p...
International audienceThis paper investigates the limit behavior of Markov decision processes made o...
We consider mean-field control problems in discrete time with discounted reward, infinite time horiz...
Optimal control provides an appealing machinery to complete complicated control tasks with limited p...
We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov...
We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov...
The mean-field game theory is the study of strategic decision making in very large populations of we...
Conclusion Motivation, description of the problem A Markov Decision Process We consider: System of N...
International audienceThis paper investigates the limit behavior of Markov decision processes made o...
We formally verify executable algorithms for solving Markov decision processes (MDPs) in the interac...
International audienceWe study the convergence of Markov decision processes, composed of a large num...
Abstract—We study the convergence of Markov decision pro-cesses, composed of a large number of objec...
We study the convergence of Markov decision processes, composed of a large number of objects, to opt...
We consider a finite number of $N$ statistically equal individuals, each moving on a finite set of s...
Abstract. State-based systems with discrete or continuous time are of-ten modelled with the help of ...
This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent p...
International audienceThis paper investigates the limit behavior of Markov decision processes made o...
We consider mean-field control problems in discrete time with discounted reward, infinite time horiz...
Optimal control provides an appealing machinery to complete complicated control tasks with limited p...
We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov...
We derive a new expectation maximization algorithm for policy optimization in linear Gaussian Markov...
The mean-field game theory is the study of strategic decision making in very large populations of we...
Conclusion Motivation, description of the problem A Markov Decision Process We consider: System of N...
International audienceThis paper investigates the limit behavior of Markov decision processes made o...
We formally verify executable algorithms for solving Markov decision processes (MDPs) in the interac...