?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Physically+Embedded+Genetic+Algorithm+Learning+in+Multi-Robot+Scenarios%3A+The+PEGA+algorithm&rft.creator=Nehmzow%2C+Ulrich&rft.subject=Machine+Learning&rft.subject=Artificial+Intelligence&rft.subject=Robotics&rft.description=We+present+experiments+in+which+a+group+of+autonomous+mobile+robots+learn+to+perform+fundamental+sensor-motor+tasks+through+a+collaborative+learning+process.+Behavioural+strategies%2C+i.e.+motor+responses+to+sensory+stimuli%2C+are+encoded+by+means+of+genetic+strings+stored+on+the+individual+robots%2C+and+adapted+through+a+genetic+algorithm+(Mitchell%2C+1998)+executed+by+the+entire+robot+collective%3A+robots+communicate+their+own+strings+and+corresponding+fitness+to+each+other%2C+and+then+execute+a+genetic+algorithm+to+improve+their+individual+behavioural+strategy.%0AThe+robots+acquired+three+different+sensormotor+competences%2C+as+well+as+the+ability+to+select+one+of+two%2C+or+one+of+three+behaviours+depending+on+context+(%22behaviour+management%22).+Results+show+that+fitness+indeed+increases+with+increasing+learning+time%2C+and+the+analysis+of+the+acquired+behavioural+strategies+demonstrates+that+they+are+effective+in+accomplishing+the+desired+task.&rft.publisher=Lund+University+Cognitive+Studies&rft.contributor=Prince%2C+Christopher+G.&rft.contributor=Demiris%2C+Yiannis&rft.contributor=Marom%2C+Yuval&rft.contributor=Kozima%2C+Hideki&rft.contributor=Balkenius%2C+Christian&rft.date=2002&rft.type=Conference+Paper&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F2521%2F1%2FNehmzow.pdf&rft.identifier=++Nehmzow%2C+Ulrich++(2002)+Physically+Embedded+Genetic+Algorithm+Learning+in+Multi-Robot+Scenarios%3A+The+PEGA+algorithm.++%5BConference+Paper%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F2521%2F