?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.relation=https%3A%2F%2Fpure.iiasa.ac.at%2Fid%2Feprint%2F4179%2F&rft.title=Learning+Dynamics+in+Games+with+Stochastic+Perturbations&rft.creator=Kaniovski%2C+Y.M.&rft.creator=Young%2C+H.P.&rft.description=Consider+a+game+that+is+played+repeatedly+by+two+populations+of+agents.+In+fictitious+play%2C+agents+learn+by+choosing+best+replies+to+the+frequency+distribution+of+actions+taken+by+the+other+side.+We+consider+a+more+general+class+of+learning+processes+in+which+agents'+choices+are+perturbed+by+incomplete+information+about+what+the+other+side+has+done%2C+variability+in+their+payoffs%2C+and+unexplained+trembles.+These+perturbed+best+reply+dynamics+define+a+non-stationary+Markov+process+on+an+infinite+state+space.+We+show+that+for+2x2+games+it+converges+with+probability+one+to+a+neighborhood+of+the+stable+Nash+equilibria%2C+whether+pure+or+mixed.+This+generalizes+a+result+of+Fudenberg+and+Kreps%2C+who+demonstrate+convergence+when+the+game+has+a+unique+mixed+equilibrium.&rft.publisher=WP-94-030&rft.date=1994-12&rft.type=Monograph&rft.type=NonPeerReviewed&rft.format=text&rft.language=en&rft.identifier=https%3A%2F%2Fpure.iiasa.ac.at%2Fid%2Feprint%2F4179%2F1%2FWP-94-030.pdf&rft.identifier=++Kaniovski%2C+Y.M.+%3Chttps%3A%2F%2Fpure.iiasa.ac.at%2Fview%2Fiiasa%2F2009.html%3E+%26+Young%2C+H.P.+%3Chttps%3A%2F%2Fpure.iiasa.ac.at%2Fview%2Fiiasa%2F2539.html%3E++(1994).++Learning+Dynamics+in+Games+with+Stochastic+Perturbations.+++IIASA+Working+Paper.+IIASA%2C+Laxenburg%2C+Austria%3A+WP-94-030+++++