Collaborated with:S.M.Lucas Egill Orn Jonsson J.J.M.Guervós A.M.Mora C.Cotta
Talks about:learn (4) differ (3) evalu (3) trajectori (2) function (2) othello (2) versus (2) tempor (2) posit (2) play (2)
Person: Thomas Philip Runarsson
DBLP: Runarsson:Thomas_Philip
Contributed to:
20062007201020122015Wrote 5 papers:
- CIG-2006-LucasR #co-evolution #difference #evaluation #learning
- Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation (SML, TPR), pp. 52–59.
- CIG-2007-RunarssonJ #evaluation #learning #using
- Effect of look-ahead search depth in learning position evaluation functions for Othello using -greedy exploration (TPR, EOJ), pp. 210–215.
- CIG-2010-GuervosMRC #game studies #performance
- Assessing efficiency of different evolutionary strategies playing MasterMind (JJMG, AMM, TPR, CC), pp. 38–45.
- CIG-2012-RunarssonL #difference #game studies #learning
- Imitating play from game trajectories: Temporal difference learning versus preference learning (TPR, SML), pp. 79–82.
- CIG-2015-RunarssonL #approximate #evaluation #game studies #on the #using
- On imitating Connect-4 game trajectories using an approximate n-tuple evaluation function (TPR, SML), pp. 208–213.