Competing with humans at fantasy football: team formation in large partially-observable domains


Matthews, Tim, Ramchurn, Sarvapali and Chalkiadakis, Georgios (2012) Competing with humans at fantasy football: team formation in large partially-observable domains. In, Twenty-Sixth Conference of the Association for the Advancement for Artificial Intelligence, Toronto, CA, 22 - 26 Jul 2012. Palo Alto, US, Association for the Advancement of Artificial Intelligence8pp, 1394-1400.

Download

[img]
Preview
PDF - Other
Download (377Kb)

Description/Abstract

We present the first real-world benchmark for sequentially optimal team formation, working within the framework of a class of online football prediction games known as Fantasy Football. We model the problem as a Bayesian reinforcement learning one, where the action space is exponential in the number of players and where the decision maker’s beliefs are over multiple characteristics of each footballer. We then exploit domain knowledge to construct computationally tractable solution techniques in order to build a competitive automated Fantasy Football manager. Thus, we are able to establish the baseline performance in this domain, even without complete information on footballers’ performances (accessible to human managers), showing that our agent is able to rank at around the top percentile when pitched against 2.5M human players

Item Type: Conference or Workshop Item (Paper)
Related URLs:
Keywords: multi-agent systems, team formation, optimisation, sequential decision making
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Agents, Interactions & Complexity
ePrint ID: 340382
Date Deposited: 22 Jun 2012 09:10
Last Modified: 27 Mar 2014 20:22
Publisher: Association for the Advancement of Artificial Intelligence
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/340382

Actions (login required)

View Item View Item