Concept

Markov decision process

Related publications (162)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Sparse reward processes

Christos Dimitrakakis

We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is a relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Cons ...

arxiv2012

Polarization in the presence of memory

Eren Sasoglu

It is shown that Arikan's recursive construction polarizes all q-ary, kappa-th order ergodic Markov processes for all kappa and prime q. ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2011

Robust Bayesian reinforcement learning through tight lower bounds

Christos Dimitrakakis

In the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinforcement learning problems. While utility bounds are known to exist for this ...

2011

A mean field approach for optimization in discrete time

Nicolas Gabriel Gast

This paper investigates the limit behavior of Markov decision processes made of independent objects evolving in a common environment, when the number of objects (N) goes to infinity. In the finite horizon case, we show that when the number of objects becom ...

2011

Barycentric Bounds in Stochastic Programming: Theory and Application

Daniel Kuhn

The design and analysis of efficient approximation schemes are of fundamental importance in stochastic programming research. Bounding approximations are particularly popular for providing strict error bounds that can be made small by using partitioning tec ...

Springer New York2011

An Efficient Method to Estimate the Suboptimality of Affine Controllers

Daniel Kuhn

We consider robust feedback control of time-varying, linear discrete-time systems operating over a finite horizon. For such systems, we consider the problem of designing robust causal controllers that minimize the expected value of a convex quadratic cost ...

Institute of Electrical and Electronics Engineers2011

An Efficient Method to Estimate the Suboptimality of Affine Controllers

Daniel Kuhn

Institute of Electrical and Electronics Engineers2011

Decision rules for information discovery in multi-stage stochastic programming

Daniel Kuhn

Stochastic programming and robust optimization are disciplines concerned with optimal decision-making under uncertainty over time. Traditional models and solution algorithms have been tailored to problems where the order in which the uncertainties unfold i ...

IEEE2011

Scenario-free stochastic programming with polynomial decision rules

Daniel Kuhn

Multi-stage stochastic programming provides a versatile framework for optimal decision making under uncertainty, but it gives rise to hard functional optimization problems since the adaptive recourse decisions must be modeled as functions of some or all un ...

IEEE2011

Mean field for Markov Decision Processes: from Discrete to Continuous Optimization

Jean-Yves Le Boudec, Nicolas Gabriel Gast

We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal reward of such a Markov Decision Process, satisfying a Bellman equation, con ...

2010