Skip to Main content Skip to Navigation
New interface
Conference papers

Abstraction Pathologies In Markov Decision Processes

Manel Tagorti 1 Bruno Scherrer 1 Olivier Buffet 1 Joerg Hoffmann 1, 2 
1 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Olivier Buffet Connect in order to contact the contributor
Submitted on : Thursday, November 21, 2013 - 10:09:38 AM
Last modification on : Saturday, June 25, 2022 - 7:42:59 PM
Long-term archiving on: : Saturday, February 22, 2014 - 4:32:30 AM


Publisher files allowed on an open archive


  • HAL Id : hal-00907315, version 1



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⟩



Record views


Files downloads