Application of Manifold Learning methods to scene information in video games

We have shown that the Isomap, one of the most famous Manifold Learning method, is suitable for Neu-roevolution of mobile robots with redundant inputs. In the proposed method, a large number of high dimensional inputs are collected in advance. The Manifold Learning method yields the low dimensional space. Evolutionary Learning is carried out with the low dimensional inputs, instead of the original high dimensional inputs. In this paper, the Isomap and Manifold Sculpting are compared by using Mario AI Championship.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  Julian Togelius,et al.  The WCCI 2008 simulated car racing competition , 2008, 2008 IEEE Symposium On Computational Intelligence and Games.

[3]  S.M. Lucas,et al.  Evolutionary computation and games , 2006, IEEE Computational Intelligence Magazine.

[4]  Tadashi Horiuchi,et al.  Adaptive state construction for reinforcement learning and its application to robot navigation problems , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[5]  Daisuke Sasaki,et al.  Visualization and Data Mining of Pareto Solutions Using Self-Organizing Map , 2003, EMO.

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

[7]  Julian Togelius,et al.  The 2007 IEEE CEC simulated car racing competition , 2008, Genetic Programming and Evolvable Machines.

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  Tomoyuki Hiroyasu,et al.  Distributed Probabilistic Model-Building Genetic Algorithm , 2003, GECCO.

[10]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[11]  Tony R. Martinez,et al.  Iterative Non-linear Dimensionality Reduction with Manifold Sculpting , 2007, NIPS.

[12]  M. Clerc,et al.  The swarm and the queen: towards a deterministic and adaptive particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[13]  Hisashi Handa.  On the effect of dimensionality reduction by Manifold Learning for Evolutionary Learning , 2011, Evol. Syst..

[14]  Julian Togelius,et al.  Super mario evolution , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[15]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[16]  Julian Togelius,et al.  The 2009 Mario AI Competition , 2010, IEEE Congress on Evolutionary Computation.

[17]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[18]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[19]  Seiichi Kawata,et al.  A teaching method using a self-organizing map for reinforcement learning , 2006, Artificial Life and Robotics.

[20]  Tughrul Arslan,et al.  IEEE Congress on Evolutionary Computation, CEC 2021, Kraków, Poland, June 28 - July 1, 2021 , 2021, IEEE Congress on Evolutionary Computation.

[21]  Simon M. Lucas,et al.  Evolving a Neural Network Location Evaluator to Play Ms. Pac-Man , 2005, CIG.

[22]  Clare Bates Congdon,et al.  REALM: A rule-based evolutionary computation agent that learns to play Mario , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[23]  Hamid Beigy,et al.  Using PCA to improve evolutionary cellular automata algorithms , 2008, GECCO '08.

[24]  X. Huo,et al.  A Survey of Manifold-Based Learning Methods , 2007 .