Back to Search
Start Over
Monte-Carlo simulation balancing revisited
- Source :
- CIG
- Publication Year :
- 2016
- Publisher :
- IEEE, 2016.
-
Abstract
- Simulation Balancing is an optimization algorithm to automatically tune the parameters of a playout policy used inside a Monte Carlo Tree Search. The algorithm fits a policy so that the expected result of a policy matches given target values of the training set. Up to now it has been successfully applied to Computer Go on small 9 × 9 boards but failed for larger board sizes like 19 × 19. On these large boards apprenticeship learning, which fits a policy so that it closely follows an expert, continues to be the algorithm of choice. In this paper we introduce several improvements to the original simulation balancing algorithm and test their effectiveness in Computer Go. The proposed additions remove the necessity to generate target values by deep searches, optimize faster and make the algorithm less prone to overfitting. The experiments show that simulation balancing improves the playing strength of a Go program using apprenticeship learning by more than 200 ELO on the large board size 19 × 19.
- Subjects :
- Imagination
Computer science
media_common.quotation_subject
Monte Carlo tree search
Monte Carlo method
Approximation algorithm
0102 computer and information sciences
02 engineering and technology
Overfitting
01 natural sciences
Search engine
Apprenticeship learning
010201 computation theory & mathematics
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Algorithm
Computer Go
Simulation
media_common
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2016 IEEE Conference on Computational Intelligence and Games (CIG)
- Accession number :
- edsair.doi...........010d580ae8f24c384930c3a0ddf80ec0