000220677 001__ 220677
000220677 005__ 20190317000512.0
000220677 0247_ $$2doi$$a10.1145/2908961.2931673
000220677 02470 $$2ISI$$a000383741800140
000220677 037__ $$aCONF
000220677 245__ $$aDarwinian Dynamics of Embodied Chaotic Exploration
000220677 269__ $$a2016
000220677 260__ $$bACM Press$$c2016$$aNew York, New York, USA
000220677 300__ $$a4
000220677 336__ $$aConference Papers
000220677 520__ $$aWe present Embodied Chaotic Exploration (ECE), a novel direction of research into a possible candidate for Darwinian neural dynamics, where such dynamics are occurring not at the level of synaptic connections, but rather at the slightly higher and more abstract level of embodied motor pattern attractors. Crucially, the (chaotic) neuro dynamics are embodied and it is the whole neuro-body-environment system that must be considered, although the changes occur at the neural level. ECE incrementally explores and learns motor behaviors through an integrated combination of chaotic search and reflex learning. The architecture developed here allows real-time, goal-directed exploration and learning of the possible motor patterns (e.g. for locomotion) of embodied systems of arbitrary morphology. The overall iterative search process formed from this combination is shown to have strong parallels with evolutionary search.
000220677 6531_ $$aEvolutionary Computation
000220677 6531_ $$aEvolution
000220677 6531_ $$aCognition
000220677 6531_ $$aDarwinian Neurodynamics
000220677 6531_ $$aNeuronal Darwisnism
000220677 6531_ $$aRobotics
000220677 700__ $$aShim, Yoonsik
000220677 700__ $$aAuerbach, Joshua E.
000220677 700__ $$aHusbands, Phil
000220677 7112_ $$d20-24 07 2016$$cDenver, Colorado, USA$$aGECCO '16
000220677 773__ $$tProceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion - GECCO '16 Companion$$q1053-1056
000220677 8564_ $$uhttps://infoscience.epfl.ch/record/220677/files/p1053-shim.pdf$$zPublisher's version$$s3102231$$yPublisher's version
000220677 909C0 $$xU10370$$0252161$$pLIS
000220677 909CO $$ooai:infoscience.tind.io:220677$$qGLOBAL_SET$$pconf$$pSTI
000220677 917Z8 $$x239571
000220677 937__ $$aEPFL-CONF-220677
000220677 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000220677 980__ $$aCONF