?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Towards+self-organising+Action+Selection&rft.creator=Humphrys%2C+Mark&rft.subject=Animal+Behavior&rft.subject=Ethology&rft.subject=Artificial+Intelligence&rft.subject=Dynamical+Systems&rft.subject=Machine+Learning&rft.subject=Robotics&rft.description=Systems+with+multiple+parallel+goals+(e.g.+autonomous+mobile+robots)+have+a+problem+analogous+to+that+of+action+selection+in+ethology.+Architectures+such+as+the+subsumption+architecture+(Brooks)+involve+multiple+sensing-and-acting+agents+within+a+single+robot+on+its+own+if+allowed.+Which+to+give+control+at+a+given+moment+is+normally+regarded+as+a+(difficult)+problem+of+design.+In+a+quest+for+a+scheme+where+the+agents+decide+for+themselves+in+a+sensible+manner%2C+I+introduce+a+model+where+the+agents+are+not+only+autonomous+but+are+in+full+competition+with+each+other+for+control+of+the+robot.+Interesting+robots+are+ones+where+no+agent+achieves+total+victory%2C+but+rather+a+serires+of+compromises+are+reached.+Having+the+agents+operate+by+the+reinforcement+learning+algorithm+Q-learning+(Watkins)+allows+the+introduction+of+an+algorithm+called+%60W-learning'%2C+by+which+the+agents+learn+to+focus+their+competitive+efforts+in+a+manner+similar+to+agents+with+limited+spending+power+in+an+economy.+In+this+way%2C+the+population+of+agents+organises+its+own+action+selection+in+a+coherent+way+that+supports+parallelism+and+opportunism.+In+the+empirical+section%2C+I+show+how+the+relative+influence+an+agent+has+on+its+robot+may+be+controlled+by+adjusting+its+rewards.+The+possibility+of+automated+search+of+agent-combinations+is+considered.&rft.date=1995&rft.type=Departmental+Technical+Report&rft.type=NonPeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F450%2F2%2Fe.planning.scheduling.ps&rft.identifier=++Humphrys%2C+Mark++(1995)+Towards+self-organising+Action+Selection.++%5BDepartmental+Technical+Report%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F450%2F