Evolving Symbolic Controllers

The idea of symbolic controllers tries to bridge the gap between the top-down manual design of the controller architecture, as advocated in Brooks' subsumption architecture, and the bottom-up designer-free approach that is now standard within the Evolutionary Robotics community. The designer provides a set of elementary behavior, and evolution is given the goal of assembling them to solve complex tasks. Two experiments are presented, demonstrating the efficiency and showing the recursiveness of this approach. In particular, the sensitivity with respect to the proposed elementary behaviors, and the robustness w.r.t. generalization of the resulting controllers are studied in detail.

[1]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[2]  Stefano Nolfi,et al.  How Co-Evolution can Enhance the Adaptive Power of Artificial Evolution: Implications for Evolutionary Robotics , 1998, EvoRobot.

[3]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[4]  José del R. Millán,et al.  Continuous-Action Q-Learning , 2002, Machine Learning.

[5]  Inman Harvey,et al.  The artificial evolution of adaptive behaviour , 1994 .

[6]  Inman Harvey,et al.  Evolving integrated controllers for autonomous learning robots using dynamic neural networks , 2002 .

[7]  Maja J. Matarić,et al.  Action Selection methods using Reinforcement Learning , 1996 .

[8]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[9]  Hans-Paul Schwefel,et al.  Numerical Optimization of Computer Models , 1982 .

[10]  Randall D. Beer,et al.  Integrating reactive, sequential, and learning behavior using dynamical neural networks , 1994 .

[11]  S. Griffis.  EDITOR , 1997, Journal of Navigation.

[12]  Maarten Keijzer,et al.  Evolving Objects: A General Purpose Evolutionary Computation Library , 2001, Artificial Evolution.

[13]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[14]  R. Dawkins.  The Blind Watchmaker , 1986 .

[15]  Richard S. Sutton,et al.  Dimensions of Reinforcement Learning , 1998 .

[16]  Peter J. Bentley,et al.  Aspects of Evolutionary Design by Computers , 1998, ArXiv.

[17]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[18]  D. Floreano,et al.  Evolutionary Robotics: The Biology,Intelligence,and Technology , 2000 .

[19]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[20]  Peter J. Bentley,et al.  Evolutionary Design by Computers with CDrom , 1999 .

[21]  Pattie Maes,et al.  The Dynamics of Action Selection , 1989, IJCAI.