Interactive POMDPs: Properties and Preliminary Results

This paper presents properties and results of a new framework for sequential decision-making in multiagent settings called interactive partially observable Markov decision processes (I-POMDPs). I-POMDPs are generalizations of POMDPs, a well-known framework for decision-theoretic planning in uncertai...

Full description

Saved in:
Bibliographic Details
Main Authors: Gmytrasiewicz, Piotr J., Doshi, Prashant
Format: Conference Proceeding
Language:English
Subjects:
Applied computing > Operations research > Decision analysis
Artificial intelligence
Computer science
Computing methodologies > Artificial intelligence > Distributed artificial intelligence > Multi-agent systems
Decision making
Engineering profession
Equations
Game theory
Information systems > Information systems applications > Decision support systems
Mathematics of computing > Probability and statistics > Probabilistic representations > Markov networks
Mathematics of computing > Probability and statistics > Stochastic processes > Markov processes
Multiagent systems
Piecewise linear techniques
Probability distribution
Stochastic processes
Theory of computation > Theory and algorithms for application domains > Machine learning theory > Markov decision processes
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents properties and results of a new framework for sequential decision-making in multiagent settings called interactive partially observable Markov decision processes (I-POMDPs). I-POMDPs are generalizations of POMDPs, a well-known framework for decision-theoretic planning in uncertain domains, to cases when an agent needs to plan a course of action in an environment populated by other agents.
DOI:10.5555/1018411.1018948