OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Markov Decision Processes

Garcia, Frédérick and Rachelson, Emmanuel Markov Decision Processes. (2010) In: Markov Decision Processes in Artificial Intelligence. John Wiley & Sons, Inc., 3-38. ISBN 978-1-84821-167-4

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1002/9781118557426.ch1


A Markov decision process (MDP) relies on the notions of state, describing the current situation of the agent, action affecting the dynamics of the process, and reward, observed for each transition between states. This chapter presents the basics of MDP theory and optimization, in the case of an agent having a perfect knowledge of the decision process and of its state at every time step, when the agent’s goal is to maximize its global revenue over time. Solving a Markov decision problem implies searching for a policy, in a given set, which optimizes a performance criterion for the considered MDP. The main criteria studied in the theory of MDPs are: finite criterion, discounted criterion, total reward criterion and average criterion. The chapter successively characterizes optimal policies for each of the above criteria, and presents adapted algorithms to obtain the optimal policies.

Item Type:Book Section
Uncontrolled Keywords:
Institution:French research institutions > Institut National de la Recherche Agronomique - INRA (FRANCE)
Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE)
Laboratory name:
Deposited On:27 Sep 2017 10:56

Repository Staff Only: item control page