Article

 

PAC Optimal MDP Planning with Application to Invasive Species Management Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/articles/1c18dh59v

Descriptions

Attribute NameValues
Creator
Abstract
  • In a simulator-defined MDP, the Markovian dynamics and rewards are provided in the form of a simulator from which samples can be drawn. This paper studies MDP planning algorithms that attempt to minimize the number of simulator calls before terminating and outputting a policy that is approximately optimal with high probability. The paper introduces two heuristics for efficient exploration and an improved confidence interval that enables earlier termination with probabilistic guarantees. We prove that the heuristics and the confidence interval are sound and produce with high probability an approximately optimal policy in polynomial time. Experiments on two benchmark problems and two instances of an invasive species management problem show that the improved confidence intervals and the new search heuristics yield reductions of between 8% and 47% in the number of simulator calls required to reach near-optimal policies.
  • This is the publisher’s final pdf. The published article is copyrighted by the author(s) and published by Journal of Machine Learning Research, Microtome Publishing. The published article can be found at: http://www.jmlr.org/
  • Keywords: invasive species management, Good-Turing estimate, MDP planning, Markov decision processes, reinforcement learning
Resource Type
Date Available
Date Issued
Citation
  • Taleghan, M. A., Dietterich, T. G., Crowley, M., Hall, K., & Albers, H. J. (2015). PAC Optimal MDP Planning with Application to Invasive Species Management. Journal of Machine Learning Research, 16, 3877-3903.
Journal Title
Journal Volume
  • 16
Rights Statement
Funding Statement (additional comments about funding)
  • This material is based upon work supported by the National Science Foundation under Grants 0832804 and 1331932.
Publisher
Peer Reviewed
Language
Replaces

Relationships

Parents:

This work has no parents.

Items