Naïve creature learns to cross a highway in a simulated CA-like environment

We present a model of simple cognitive agents, called “creatures”, and their learning process, a type of “social observational learning”, that is each creature learns from the behaviour of other creatures. The creatures may experience fear and/or desire, and are capable of evaluating if a strategy has been applied successfully and of applying this strategy again with small changes to a similar but new situation. The creatures are born as “tabula rasa”; i.e. without built-in knowledge base of their environment and as they learn they build this knowledge base. We study learning outcomes of a population of such creatures when they are learning how to safely cross various types of highways. The highways are implemented as a modified Nagel-Schreckenberg model, a CA based highway model, and each creature is provided with mechanism to reason to cross safely the highway. We present selected simulation results and their analysis.

[1]  Anna T. Lawniczak,et al.  Computational intelligence based architecture for cognitive agents , 2010, ICCS.

[2]  Barbara Messing,et al.  An Introduction to MultiAgent Systems , 2002, Künstliche Intell..

[3]  Jacques Ferber,et al.  Multi-agent systems - an introduction to distributed artificial intelligence , 1999 .

[4]  Michael Schreckenberg,et al.  A cellular automaton model for freeway traffic , 1992 .

[5]  Anna T. Lawniczak,et al.  Creature Learning to Cross a CA Simulated Road , 2012, ACRI.

[6]  Danny Weyns,et al.  Multi-Agent Systems , 2009 .

[7]  Wolfgang Heenes,et al.  GCA: a massively parallel model , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[8]  D. O A L O N S O,et al.  Learning in multi-agent systems , 2002 .

[9]  M Cremer,et al.  A fast simulation model for traffic flow on the basis of Boolean operations , 1986 .

[10]  Karolin Baecker,et al.  Cellular Automata Modeling Of Physical Systems , 2016 .

[11]  Anna T. Lawniczak,et al.  Cognitive agents: Functionality & performance requirements and a proposed software architecture , 2009, 2009 IEEE Toronto International Conference Science and Technology for Humanity (TIC-STH).

[12]  Bastien Chopard,et al.  Cellular Automata Modeling of Physical Systems: Index , 1998 .

[13]  M J Lighthill,et al.  On kinematic waves II. A theory of traffic flow on long crowded roads , 1955, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[14]  H. Fuks.  Solution of the density classification problem with two cellular automata rules , 1997, comp-gas/9703001.

[15]  Stefan Waldschmidt,et al.  Global Cellular Automata GCA: An Universal Extension of the CA Model , 2000 .

[16]  Anna T. Lawniczak,et al.  Simulated Naïve Creature Crossing a Highway , 2013, ICCS.

[17]  Stefan Waldschmidt,et al.  GCA: Global Cellular Automata. A Flexible Parallel Model , 2001, PaCT.

[18]  Radhika Nagpal,et al.  Programmable self-assembly in a thousand-robot swarm , 2014, Science.

[19]  Radhika Nagpal,et al.  Kilobot: A low cost scalable robot system for collective behaviors , 2012, 2012 IEEE International Conference on Robotics and Automation.

[20]  Anastasios Xepapadeas,et al.  Modeling Complex Systems , 2010 .

[21]  Anna T. Lawniczak,et al.  Naïve Creature with Fear and Desire Learning to Cross a Highway , 2014, ICCS.

[22]  D. de Cogan,et al.  Cellular Automata Modelling of Physical Systems, by Bastien Chopard & Michel Droz, Cambridge University Press (Aléa Saclay Collection), 336 pp., ISBN 0‐521‐46168‐5, hardback, £55 , 2000 .

[23]  Daniel M. Helmick,et al.  Autonomy for Mars Rovers: Past, Present, and Future , 2008, Computer.

[24]  P. I. Richards.  Shock Waves on the Highway , 1956 .

[25]  Anna T. Lawniczak,et al.  Multilane Single GCA-w Based Expressway Traffic Model , 2010, ACRI.

[26]  Gerhard Weiss,et al.  Multi-Agent Systems , 2013 .