neural networks research group
areas
people
projects
demos
publications
software/data
Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree (2011)
Doran Chakraborty
and
Peter Stone
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.
View:
PDF
,
PS
,
HTML
Citation:
In
Proceedings of the Twenty Eighth International Conference on Machine Learning (ICML'11)
, June 2011.
Bibtex:
@inproceedings{ICML11-chakraborty, title={Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree}, author={Doran Chakraborty and Peter Stone}, booktitle={Proceedings of the Twenty Eighth International Conference on Machine Learning (ICML'11)}, month={June}, url="http://nn.cs.utexas.edu/?ICML11-chakraborty", year={2011} }
People
Doran Chakraborty
chakrado [at] cs utexas edu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Agent Modeling in Multiagent Systems
Reinforcement Learning