A developmental model for the evolution of complete autonomous agents Export

@inproceedings{citeulike:4234937, abstract = {Development is an important, powerful and integral element of biological evolution. In this paper we present two models of development that can be used to evolve functional autonomous agents, complete with bodies and neural control systems. The first and most complex model is more biologically defensible in its details. It has been used to hand-design a genome for the development of complete agents capable of executing a simple avoidance task. These agents were then incrementally improved through evolution. The second model is simpler and uses a random Boolean network model for the genome and cell state that is somewhat more removed from the biological realm, making it easier to analyze and more amenable to artificial evolution. Using this model, we have successfully evolved complete agents from scratch that are capable of following curved lines. 1.}, author = {Dellaert, Frank and Beer, All D.}, booktitle = {Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior}, citeulike-article-id = {4234937}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.571}, keywords = {agents, alife, brain, development, evolution}, pages = {393--401}, posted-at = {2009-03-29 11:30:17}, priority = {2}, title = {A developmental model for the evolution of complete autonomous agents}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.571}, year = {1996} }

TY - CONF ID - citeulike:4234937 L3 - citeulike-article-id:4234937 N2 - Development is an important, powerful and integral element of biological evolution. In this paper we present two models of development that can be used to evolve functional autonomous agents, complete with bodies and neural control systems. The first and most complex model is more biologically defensible in its details. It has been used to hand-design a genome for the development of complete agents capable of executing a simple avoidance task. These agents were then incrementally improved through evolution. The second model is simpler and uses a random Boolean network model for the genome and cell state that is somewhat more removed from the biological realm, making it easier to analyze and more amenable to artificial evolution. Using this model, we have successfully evolved complete agents from scratch that are capable of following curved lines. 1. EP - 401 TI - A developmental model for the evolution of complete autonomous agents T2 - Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior SP - 393 KW - agents KW - alife KW - brain KW - development KW - evolution AU - Dellaert, Frank AU - Beer, All PY - 1996/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.571 ER -