Evolving neural networks for geometric game-tree pruning

Abstract Game-tree search is the engine behind many computer game opponents. Traditional game-tree search algorithms decide which move to make based on simulating actions, evaluating future board states, and then applying the evaluations to estimate optimal play by all players. Yet the limiting factor of such algorithms is that the search space increases exponentially with the number of actions taken (i.e. the depth of the search). More recent research in game-tree search has revealed that even more important than evaluating future board states is effective pruning of the search space. Accordingly, this paper discusses Geometric Game-Tree Pruning (GGTP), a novel evolutionary method that learns to prune game trees based on geometric properties of the game board. The experiment compares Cake, a minimax-based game-tree search algorithm, with HyperNEAT-Cake, the original Cake algorithm combined with an indirectly encoded, evolved GGTP algorithm. The results show that HyperNEAT-Cake wins significantly more games than regular Cake playing against itself.

[1]  Risto Miikkulainen,et al.  A Taxonomy for Artificial Embryogeny , 2003, Artificial Life.

[2]  Kenneth O. Stanley,et al.  A novel generative encoding for exploiting neural network sensor and output geometry , 2007, GECCO '07.

[3]  Kenneth O. Stanley,et al.  Compositional Pattern Producing Networks : A Novel Abstraction of Development , 2007 .

[4]  Kenneth O. Stanley,et al.  Generating large-scale neural networks through discovering geometric regularities , 2007, GECCO '07.

[5]  A. K. Dewdney,et al.  New Turing Omnibus , 1993 .

[6]  Jordan B. Pollack,et al.  Creating High-Level Components with a Generative Representation for Body-Brain Evolution , 2002, Artificial Life.

[7]  Risto Miikkulainen,et al.  Evolving a Roving Eye for Go , 2004, GECCO.

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

[9]  Josh Bongard,et al.  Evolving modular genetic regulatory networks , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[10]  Kenneth O. Stanley,et al.  Indirect Encoding of Neural Networks for Scalable Go , 2010, PPSN.

[11]  Kenneth O. Stanley.  A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks , 2009 .

[12]  Kenneth O. Stanley,et al.  A Case Study on the Critical Role of Geometric Regularity in Machine Learning , 2008, AAAI.

[13]  Kenneth O. Stanley,et al.  Autonomous Evolution of Topographic Regularities in Artificial Neural Networks , 2010, Neural Computation.

[14]  Chien-Ping Paul. Lu,et al.  Parallel search of narrow game trees , 1993 .

[15]  Donald E. Knuth,et al.  The Solution for the Branching Factor of the Alpha-Beta Pruning Algorithm , 1981, ICALP.

[16]  David Silver,et al.  Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (2008) Achieving Master Level Play in 9 × 9 Computer Go , 2022 .

[17]  David Silver,et al.  Combining online and offline knowledge in UCT , 2007, ICML '07.

[18]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[19]  Peter J. Bentley,et al.  Three Ways to Grow Designs: A Comparison of Embryogenies for an Evolutionary Design Problem , 1999, GECCO.

[20]  Kenneth O. Stanley,et al.  Generative encoding for multiagent learning , 2008, GECCO '08.

[21]  David Silver,et al.  Combining Online and Offline Learning in UCT , 2007 .

[22]  David B. Fogel,et al.  Blondie24: Playing at the Edge of AI , 2001 .

[23]  Risto Miikkulainen,et al.  Continual Coevolution Through Complexification , 2002, GECCO.

[24]  Janet Wiles,et al.  The challenge of Go as a domain for AI research: a comparison between Go and chess , 1995, Proceedings of Third Australian and New Zealand Conference on Intelligent Information Systems. ANZIIS-95.

[25]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

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