Abstraction Pathologies In Markov Decision Processes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Abstraction Pathologies In Markov Decision Processes

Manel Tagorti
  • Function : Author
  • PersonId : 948730
Bruno Scherrer
Olivier Buffet

Abstract

Abstraction is a common method to compute lower bounds in classical planning, imposing an equivalence relation on the state space and deriving the lower bound from the quotient system. It is a trivial and well-known fact that refined abstractions can only improve the lower bound. Thus, when we embarked on applying the same technique in the probabilistic setting, our firm belief was to find the same behavior there. We were wrong. Indeed, there are cases where every direct refinement step (splitting one equivalence class into two) yields strictly worse bounds. We give a comprehensive account of the issues involved, for two wide-spread methods to define and use abstract MDPs.
Fichier principal
Vignette du fichier
hsdip13.pdf (129.93 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00907315 , version 1 (21-11-2013)

Identifiers

  • HAL Id : hal-00907315 , version 1

Cite

Manel Tagorti, Bruno Scherrer, Olivier Buffet, Joerg Hoffmann. Abstraction Pathologies In Markov Decision Processes. ICAPS'13 workshop on Heuristics and Search for Domain-independent Planning (HSDIP), Jun 2013, Rome, Italy. ⟨hal-00907315⟩
112 View
93 Download

Share

Gmail Facebook X LinkedIn More