Logo image
Sign in
Approximations on Risk-Averse Markov Decision Processes
Report   Open access

Approximations on Risk-Averse Markov Decision Processes

Eugenio Della Vecchia, Silvia C. Di Marco and Alain Jean-Marie
18/11/2013

Abstract

Markov Decision Processes Rolling Horizon risk aversion
We consider the problem of approximating the values and the optimal policies in risk-averse discounted Markov Decision Processes with in nite horizon. We study the properties of the rolling horizon and the approximate rolling horizon procedures, proving bounds which imply the convergence of the procedures when the horizon length tends to in nity. We also analyze the e ects of uncertainties on the transition probabilities, the cost functions and the discount factors.
url
Find in HALView

Metrics

1 Record Views

Details

Logo image