An Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model Export

@article{TuciQuinnHarvey2002KappaPaper, abstract = {We are interested in the construction of ecological models of the evolution of learning behavior using methodological tools developed in the field of evolutionary robotics. In this article, we explore the applicability of integrated (i.e., nonmodular) neural networks with fixed connection weights and simple 'leaky-integrator' neurons as controllers for autonomous learning robots. In contrast to Yamauchi and Beer (1994a), we show that such a control system is capable of integrating reactive and learned behaviour without explicitly needing hand-designed modules, dedicated to a particular behavior, or an externally introduced reinforcement signal. In our model, evolutionary and ecological contingencies structure the controller and the behavioral responses of the robot. This allows us to concentrate on examining the conditions under which learning behavior evolves.}, author = {Tuci, Elio and Quinn, Matt and Harvey, Inman}, citeulike-article-id = {229152}, citeulike-linkout-0 = {http://adb.sagepub.com/cgi/content/abstract/10/3-4/201}, comment = {this paper picks up from old Yamauchi \& Beer work, and succeeds at some things Y\&B couldn't do, but it changes so many parameters at once that it's not clear which are necessary changes.}, journal = {Adaptive Behavior}, keywords = {attention, evolutionary\_robotics, learning, neural\_control}, number = {3-4}, pages = {201--221}, posted-at = {2005-06-16 07:32:54}, priority = {0}, title = {An Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model}, url = {http://adb.sagepub.com/cgi/content/abstract/10/3-4/201}, volume = {10}, year = {2002} }

TY - JOUR ID - TuciQuinnHarvey2002KappaPaper L3 - citeulike-article-id:229152 N2 - We are interested in the construction of ecological models of the evolution of learning behavior using methodological tools developed in the field of evolutionary robotics. In this article, we explore the applicability of integrated (i.e., nonmodular) neural networks with fixed connection weights and simple 'leaky-integrator' neurons as controllers for autonomous learning robots. In contrast to Yamauchi and Beer (1994a), we show that such a control system is capable of integrating reactive and learned behaviour without explicitly needing hand-designed modules, dedicated to a particular behavior, or an externally introduced reinforcement signal. In our model, evolutionary and ecological contingencies structure the controller and the behavioral responses of the robot. This allows us to concentrate on examining the conditions under which learning behavior evolves. IS - 3-4 JF - Adaptive Behavior EP - 221 TI - An Evolutionary Ecological Approach to the Study of Learning Behavior Using a Robot-Based Model VL - 10 SP - 201 KW - attention KW - evolutionary_robotics KW - learning KW - neural_control N1 - this paper picks up from old Yamauchi & Beer work, and succeeds at some things Y&B couldn't do, but it changes so many parameters at once that it's not clear which are necessary changes. AU - Tuci, Elio AU - Quinn, Matt AU - Harvey, Inman PY - 2002/// UR - http://adb.sagepub.com/cgi/content/abstract/10/3-4/201 ER -