Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree

Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree.
Doran Chakraborty and Peter Stone.
In Proceedings of the Twenty Eighth International Conference on Machine Learning (ICML), 2011.

Download

[PDF]223.3kB  [postscript]521.1kB  

Abstract

This paper introduces Learn Structure andExploit RMax (LSE-RMax), a novel modelbased structure learning algorithm for ergodicfactored-state MDPs. Given a planninghorizon that satisfies a condition, LSE-RMaxprovably guarantees a return very close tothe optimal return, with a high certainty,without requiring any prior knowledge of thein-degree of the transition function as input.LSE-RMax is fully implemented witha thorough analysis of its sample complexity.We also present empirical results demonstratingits effectiveness compared to priorapproaches to the problem.

BibTeX Entry

@InProceedings{ICML11-chakraborty,
        author = "Doran Chakraborty and Peter Stone",
        title="Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree",
        booktitle="Proceedings of the Twenty Eighth International Conference on Machine Learning (ICML)",
        year="2011",  	        
        abstract={This paper introduces Learn Structure and
Exploit RMax (LSE-RMax), a novel model
based structure learning algorithm for ergodic
factored-state MDPs. Given a planning
horizon that satisfies a condition, LSE-RMax
provably guarantees a return very close to
the optimal return, with a high certainty,
without requiring any prior knowledge of the
in-degree of the transition function as input.
LSE-RMax is fully implemented with
a thorough analysis of its sample complexity.
We also present empirical results demonstrating
its effectiveness compared to prior
approaches to the problem. },
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Mar 25, 2024 00:05:16