An Empirical Evaluation of Policy Rollout for Clue

Graduate Project

Public Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_projects/p8418p939

Descriptions

Attribute Name	Values
Creator	Marshall, Eric
Abstract	We model the popular board game of Clue as an MDP and evaluate Monte-Carlo policy rollout in a simulated environment pitting different agents and policies against each other. We describe the choices we made in the representation, along with some of the problems we encountered along the way. We find that even a simple heuristic policy can dominate a random policy, and that single-stage rollout can be used to incrementally improve existing policies, and confirm that multi-stage rollout is not practical for this domain.
Resource Type	Capstone Project
Date Available	2016-08-09T17:55:31+00:00
Date Issued	2016-08-09
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Computer Science
Degree Grantor	Oregon State University
Commencement Year	2016
Advisor	Fern, Alan
Committee Member	Todorovic, Sinisa Tadepalli, Prasad
Academic Affiliation	Electrical Engineering and Computer Science
Déclaration de droits	In Copyright
Publisher	Oregon State Unversity
Peer Reviewed	No
Language	English [eng]
Replaces	http://hdl.handle.net/1957/59649

La vignette	Titre	Date de téléchargement	Visibilité	actes
	MarshallEricJ2016.pdf	2017-07-25	Public	Télécharger