Active learning reduces the number of playtests needed to tune game parameters for difficulty and control preference in a shoot-'em-up case study.
For enemy parameter tuning (a regression problem) we found acquisition functions that balance exploration and ex- ploitation (especially UCB) have the best performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automatic Playtesting for Game Parameter Tuning via Active Learning
Active learning reduces the number of playtests needed to tune game parameters for difficulty and control preference in a shoot-'em-up case study.