?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Trust-based+Consensus+in+Multi-Agent+Reinforcement+Learning+Systems&rft.creator=Fung%2C+Ho+Long&rft.creator=Darvariu%2C+Victor&rft.creator=Hailes%2C+Stephen&rft.creator=Musolesi%2C+Mirco&rft.description=An+often+neglected+issue+in+multi-agent+reinforcement+learning+(MARL)+is+the+potential+presence+of+unreliable+agents+in+the+environment+whose+deviations+from+expected+behavior+can+prevent+a+system+from+accomplishing+its+intended+tasks.+In+particular%2C+consensus+is+a+fundamental+underpinning+problem+of+cooperative+distributed+multi-agent+systems.+Consensus+requires+different+agents%2C+situated+in+a+decentralized+communication+network%2C+to+reach+an+agreement+out+of+a+set+of+initial+proposals+that+they+put+forward.+Learning-based+agents+should+adopt+a+protocol+that+allows+them+to+reach+consensus+despite+having+one+or+more+unreliable+agents+in+the+system.+This+paper+investigates+the+problem+of+unreliable+agents+in+MARL%2C+considering+consensus+as+a+case+study.+Echoing+established+results+in+the+distributed+systems+literature%2C+our+experiments+show+that+even+a+moderate+fraction+of+such+agents+can+greatly+impact+the+ability+of+reaching+consensus+in+a+networked+environment.+We+propose+Reinforcement+Learning-based+Trusted+Consensus+(RLTC)%2C+a+decentralized+trust+mechanism%2C+in+which+agents+can+independently+decide+which+neighbors+to+communicate+with.+We+empirically+demonstrate+that+our+trust+mechanism+is+able+to+handle+unreliable+agents+effectively%2C+as+evidenced+by+higher+consensus+success+rates.&rft.publisher=Reinforcement+Learning+Conference+Organization+Committee&rft.date=2024-08-15&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+of+the+1st+Reinforcement+Learning+Conference+(RLC'24).++(pp.+pp.+714-732).++Reinforcement+Learning+Conference+Organization+Committee%3A+Amherst%2C+MA%2C+USA.+(2024)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10194562%2F1%2Frlc24_trustbased.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10194562%2F&rft.rights=open