Approximations on Risk-Averse Markov Decision Processes

Abstract : 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.
Document type :
Reports
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-00905636
Contributor : Alain Jean-Marie <>
Submitted on : Tuesday, November 19, 2013 - 11:57:23 AM
Last modification on : Tuesday, November 13, 2018 - 2:38:01 AM
Long-term archiving on : Thursday, February 20, 2014 - 3:45:16 AM

Files

RR-8393.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00905636, version 1

Citation

Eugenio Della Vecchia, Silvia C. Di Marco, Alain Jean-Marie. Approximations on Risk-Averse Markov Decision Processes. [Research Report] RR-8393, INRIA. 2013. ⟨hal-00905636⟩

Share

Metrics

Record views

490

Files downloads

285