Thomas Philip Runarsson

Thomas Philip Runarsson

Auto-generated profile, based on publicly available information

Thomas Philip Runarsson

University of Iceland

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 June 2017 in Journal of Scheduling
Verified
Journal Article
Closed access
PDF file
Helga IngimundardóttirHelga Ingimundardóttir
Helga Ingimundardóttir
TRThomas Philip Runarsson
Thomas Philip Runarsson

1 May 2006
Verified
Conference Paper
Closed access
SLSimon M. Lucas
Simon M. Lucas
TRThomas P. Runarsson
Thomas P. Runarsson
This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othello. The paper provides important insights into the strengths and weaknesses of each approach. The main findings are that for Othello, TDL learns much faster than CEL, but that properly tuned CEL can learn better playing strategies. For CEL, it is essential to use parent-child weighted averaging in order to achieve good performance. Using this method a high quality weighted piece counter was evolved, and was shown to significantly outperform a set of standard heuristic weights

1 January 2010
Verified
Book Chapter
Closed access
PDF file
TRThomas Philip Runarsson
Thomas Philip Runarsson
JGJuan Julián Merelo Guervós
Juan Julián Merelo Guervós

1 January 2007
Verified
Conference Paper
Closed access
TRThomas Philip Runarsson
Thomas Philip Runarsson
EJEgill O. Jonsson
Egill O. Jonsson
This paper studies the effect of varying the depth of look-ahead for heuristic search in temporal difference (TD) learning and game playing. The acquisition position evaluation functions for the game of Othello is studied. The paper provides important insights into the strengths and weaknesses of using different search depths during learning when epsi-greedy exploration is applied. The main findings are that contrary to popular belief, for Othello, better playing strategies are found when TD learning is applied with lower look-ahead search depths