Robust Almost-Sure Reachability in Multi-Environment MDPs

01/26/2023
by   Marck van der Vegt, et al.
0

Multiple-environment MDPs (MEMDPs) capture finite sets of MDPs that share the states but differ in the transition dynamics. These models form a proper subclass of partially observable MDPs (POMDPs). We consider the synthesis of policies that robustly satisfy an almost-sure reachability property in MEMDPs, that is, one policy that satisfies a property for all environments. For POMDPs, deciding the existence of robust policies is an EXPTIME-complete problem. In this paper, we show that this problem is PSPACE-complete for MEMDPs, while the policies in general require exponential memory. We exploit the theoretical results to develop and implement an algorithm that shows promising results in synthesizing robust policies for various benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/30/2020

Verification of indefinite-horizon POMDPs

The verification problem in MDPs asks whether, for any policy resolving ...
research
06/24/2011

On Polynomial Sized MDP Succinct Policies

Policies of Markov Decision Processes (MDPs) determine the next action t...
research
06/13/2022

Relative Policy-Transition Optimization for Fast Policy Transfer

We consider the problem of policy transfer between two Markov Decision P...
research
05/15/2022

Reductive MDPs: A Perspective Beyond Temporal Horizons

Solving general Markov decision processes (MDPs) is a computationally ha...
research
06/13/2018

Parameter-Independent Strategies for pMDPs via POMDPs

Markov Decision Processes (MDPs) are a popular class of models suitable ...
research
09/29/2017

Sensor Synthesis for POMDPs with Reachability Objectives

Partially observable Markov decision processes (POMDPs) are widely used ...
research
09/26/2013

Qualitative Possibilistic Mixed-Observable MDPs

Possibilistic and qualitative POMDPs (pi-POMDPs) are counterparts of POM...

Please sign up or login with your details

Forgot password? Click here to reset