Evolving a Roving Eye for Go

Go remains a challenge for artiflcial intelligence. Currently, most machine learning methods tackle Go by playing on a speciflc flxed board size, usually smaller than the standard 19£19 board of the com- plete game. Because such techniques are designed to process only one board size, the knowledge gained through experience cannot be applied on larger boards. In this paper, a roving eye neural network is evolved to solve this problem. The network has a small input fleld that can scan boards of any size. Experiments demonstrate that (1) The same roving eye architecture can play on difierent board sizes, and (2) experience gained by playing on a small board provides an advantage for further learning on a larger board. These results suggest a potentially power- ful new methodology for computer Go: It may be possible to scale up by learning on incrementally larger boards, each time building on knowledge acquired on the prior board.

[1]  David E. Goldberg,et al.  Genetic Algorithms with Sharing for Multimodalfunction Optimization , 1987, ICGA.

[2]  Brad Fullmer and Risto Miikkulainen.  Using Marker-Based Genetic Encoding Of Neural Networks To Evolve Finite-State Behaviour , 1991 .

[3]  Risto Miikkulainen,et al.  Evolving Neural Networks to Focus Minimax Search , 1994, AAAI.

[4]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1994, Comput. Vis. Image Underst..

[5]  Larry D. Pyeatt,et al.  A comparison between cellular encoding and direct encoding for genetic neural networks , 1996 .

[6]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1997, Comput. Vis. Image Underst..

[7]  Benjamin Kuipers,et al.  Map Learning with Uninterpreted Sensors and Effectors , 1995, Artif. Intell..

[8]  Stefano Nolfi.  Evolving non-trivial behavior on autonomous robots: Adaptation is more powerful than decomposition a , 1997 .

[9]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.

[10]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[11]  Reid G. Simmons,et al.  Distributed visual servoing with a roving eye , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[12]  Bruno Bouzy,et al.  Computer Go: An AI oriented survey , 2001, Artif. Intell..

[13]  Jordan B. Pollack,et al.  Pareto Optimality in Coevolutionary Learning , 2001, ECAL.

[14]  Alex Lubberts and Risto Miikkulainen.  Co-Evolving a Go-Playing Neural network , 2001 .

[15]  Tristan Cazenave,et al.  Generation of Patterns With External Conditions for the Game of Go , 2001 .

[16]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning Through Evolving Neural Network Topologies , 2002, GECCO.

[17]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[18]  Markus Enzenberger,et al.  Evaluation in Go by a Neural Network using Soft Segmentation , 2003, ACG.

[19]  Risto Miikkulainen,et al.  Evolving Neural Networks to Play Go , 2004, Applied Intelligence.

[20]  Risto Miikkulainen,et al.  Competitive Coevolution through Evolutionary Complexification , 2011, J. Artif. Intell. Res..

[21]  Nicholas J. Radcliffe,et al.  Genetic set recombination and its application to neural network topology optimisation , 1993, Neural Computing & Applications.