Strategic Features for General Games

Browne, Cameron;Soemers, Dennis;Piette, Eric
(2019) Knowledge Extraction from Games — Location: Honolulu, Hawaii, USA (27.January.2019)

Files

keg19.pdf
  • Open Access
  • Adobe PDF
  • 143.32 KB
Download

Details

Authors
  • Browne, Cameron
    Author
  • Soemers, Dennis
    Author
  • Piette, EricUCLouvain
    Author
Abstract
This short paper describes an ongoing research project that requires the automated self-play learning and evaluation of a large number of board games in digital form. We describe the approach we are taking to determine relevant features, for biasing MCTS playouts for arbitrary games played on arbitrary geometries. Benefits of our approach include efficient implementation, the potential to transfer learnt knowledge to new contexts, and the potential to explain strategic knowledge embedded in features in human-comprehensible terms.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Browne, C., Soemers, D., & Piette, E. (2019). Strategic Features for General Games. Knowledge Extraction from Games, p. 70-75. https://hdl.handle.net/2078.5/253696