Evolving Neural Networks to Play Go y
نویسندگان
چکیده
Go is a di cult game for computers to master, and the best go programs are still weaker than the average human player. Since the traditional game playing techniques have proven inadequate, new approaches to computer go need to be studied. This paper presents a new approach to learning to play go. The SANE (Symbiotic, Adaptive Neuro-Evolution) method was used to evolve networks capable of playing go on small boards with no pre-programmed go knowledge. On a 9 9 go board, networks that were able to defeat a simple computer opponent were evolved within a few hundred generations. Most signi cantly, the networks exhibited several aspects of general go playing, which suggests the approach could scale up well.
منابع مشابه
Evolving Go Playing Strategy in Neural Networks
The game of Go is an ideal problem domain for exploring machine learning: it has simple rules yet requires more and more complex strategies to play well as the board size is increased. Despite much effort, existing Go programs, which have largely employed knowledge based and symbolic AI techniques, have failed to achieve a standard much above an average human amateur. This paper examines the po...
متن کاملTeaching Deep Convolutional Neural Networks to Play Go
Mastering the game of Go has remained a long standing challenge to the field of AI. Modern computer Go systems rely on processing millions of possible future positions to play well, but intuitively a stronger and more ‘humanlike’ way to play the game would be to rely on pattern recognition abilities rather then brute force computation. Following this sentiment, we train deep convolutional neura...
متن کاملTraining Deep Convolutional Neural Networks to Play Go
Mastering the game of Go has remained a longstanding challenge to the field of AI. Modern computer Go programs rely on processing millions of possible future positions to play well, but intuitively a stronger and more ‘humanlike’ way to play the game would be to rely on pattern recognition rather than brute force computation. Following this sentiment, we train deep convolutional neural networks...
متن کاملEvolving neural networks to play checkers without relying on expert knowledge
An experiment was conducted where neural networks compete for survival in an evolving population based on their ability to play checkers. More specifically, multilayer feedforward neural networks were used to evaluate alternative board positions and games were played using a minimax search strategy. At each generation, the extant neural networks were paired in competitions and selection was use...
متن کامل