Imitation learning at all levels of game-AI

Imitation is a powerful mechanism the human brain applies to extend its repertoire of solutions and behaviors suitable to solve problems of various kinds. From an abstract point of view, the major advantage of this strategy is that it reduces the search space of apropriate solutions. In this contribution, we discuss if and how the principle of imitation learning can facilitate the programing of life-like computer game charecters. We present different algorithms that learn from human generated training data and we show that machine learning can be applied on different levels of cognitive abstraction.

[1]  Christian Bauckhage,et al.  Learning Human-Like Movement Behavior for Computer Games , 2004 .

[2]  Helge J. Ritter,et al.  Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[3]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[4]  G. Rizzolatti,et al.  Hearing Sounds, Understanding Actions: Action Representation in Mirror Neurons , 2002, Science.

[5]  A. Church.  Edward F. Moore. Gedanken-experiments on sequential machines. Automata studies , edited by C. E. Shannon and J. McCarthy, Annals of Mathematics studies no. 34, litho-printed, Princeton University Press, Princeton1956, pp. 129–153. , 1958, Journal of Symbolic Logic.

[6]  George H. Mealy,et al.  A method for synthesizing sequential circuits , 1955 .

[7]  Edward F. Moore,et al.  Gedanken-Experiments on Sequential Machines , 1956 .

[8]  Georgios N. Yannakakis,et al.  Evolving opponents for interesting interactive computer games , 2004 .

[9]  Reza Shadmehr,et al.  Learning of action through adaptive combination of motor primitives , 2000, Nature.

[10]  Eyal Amir,et al.  Adventure Games: A Challenge for Cognitive Robotics , 2002 .

[11]  Maja J. Mataric,et al.  Automated Derivation of Primitives for Movement Classification , 2000, Auton. Robots.

[12]  Robert A. Jacobs,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1993, Neural Computation.

[13]  Elizabeth Sklar,et al.  Training intelligent agents using human internet data , 1999 .

[14]  Pieter Spronck,et al.  Improving Opponent Intelligence by Machine Learning , 2002 .

[15]  Tucker R. Balch,et al.  Avoiding the past: a simple but effective strategy for reactive navigation , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[16]  Jun Nakanishi,et al.  Learning Movement Primitives , 2005, ISRR.

[17]  Erik Hollnagel,et al.  Human Reliability Analysis: Context and Control , 1994 .

[18]  Christian Bauckhage,et al.  Combining Self Organizing Maps and Multilayer Perceptrons to Learn Bot-Behavior for a Commercial Computer Game , 2003 .

[19]  D. Perrett,et al.  Motion sensitive cells in the macaque superior temporal polysensory area: response discrimination between self-generated and externally generated pattern motion , 1996, Behavioural Brain Research.

[20]  Christian Bauckhage,et al.  Synthesizing Movements for Computer Game Characters , 2004, DAGM-Symposium.

[21]  Alexander Nareyek.  Computer Games - Boon or Bane for AI Research? , 2004, Künstliche Intell..

[22]  Christian Bauckhage,et al.  Learning Human-Like Opponent Behavior for Interactive Computer Games , 2003, DAGM-Symposium.

[23]  Pierre Bessière,et al.  Teaching Bayesian behaviours to video game characters , 2003, Robotics Auton. Syst..

[24]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[25]  John E. Laird,et al.  Using a Computer Game to Develop Advanced AI , 2001, Computer.