×

Optimal properties of stimulus-response learning models. (English) Zbl 1131.91308

Summary: A procedure is a specific way of making this association; a procedure is optimal if the sequence of choices it generates converges to the action that maximizes the expected payoff. The information available to the agent has crucial importance. An individual learning in isolation has partial information, because he can only observe the payoff to the action he has chosen; in social learning, he has full information, because he can learn from the action of the others. Linear procedures always converge to optimal action in the case of partial information, and do not in the case of full information. Exactly the opposite is true in the case of exponential procedures.

MSC:

91A26 Rationality and learning in game theory
91B02 Fundamental topics (basic mathematics, methodology; applicable to economics in general)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Arthur, B., Designing Economic Agents that Act like Human Agents: a Behavioral Approach to Bounded Rationality, Amer. Econ. Rev. Papers Proc., 81, 353-359 (1991)
[2] Benveniste, A.; Métivier, M.; Priouret, P., Adaptive Algorithms and Stochastic Approximations. Adaptive Algorithms and Stochastic Approximations, Applications of Mathematics, 22 (1990), Springer-Verlag: Springer-Verlag Berlin/New York · Zbl 0752.93073
[3] Billingsley, P., Convergence of Probability Measures (1968), Wiley: Wiley New York · Zbl 0172.21201
[4] Bloomfield, T. M., Reinforcement Schedules: Contingency or Contiguity?, (Gilbert, R. G.; Millenson, J. R., Reinforcement: Behavioral Analysis (1972), Academic Press: Academic Press New York), 165-208
[5] Börgers, T, Morales, A, and, Sarin, R. 1998, Simple Behavior Rules which Lead to Expected Payoff Maximizing Choices, typescript.; Börgers, T, Morales, A, and, Sarin, R. 1998, Simple Behavior Rules which Lead to Expected Payoff Maximizing Choices, typescript.
[6] Breiman, L., A Strong Law of Large Numbers for a Class of Markov Chains, Ann. Math. Statist., 31, 801-803 (1960) · Zbl 0104.11901
[7] Bush, R. R.; Mosteller, F., A Mathematical Model for Simple Learning, Psychological Rev., 58, 313-323 (1951)
[8] Bush, R. R.; Mosteller, F., A Model for Stimulus Generalization and Discrimination, Psychological Rev., 58, 413-423 (1951)
[9] Bush, R. R.; Mosteller, F., Stochastic Models for Learning (1955), Wiley: Wiley New York · Zbl 0064.39002
[10] Easley, D.; Rustichini, A., Choice without Beliefs, Econometrica (1999) · Zbl 1026.91508
[11] Erev, I. and, Roth, A. E. 1997, On the Need for Low Rationality, Cognitive Game Theory: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria, typescript.; Erev, I. and, Roth, A. E. 1997, On the Need for Low Rationality, Cognitive Game Theory: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria, typescript.
[12] Estes, K. W., Toward a Statistical Theory of Learning, Psychological Rev., 57, 94-107 (1950)
[13] Estes, K. W., Reinforcement in Human Learning, (Tapp, J., Reinforcement and Behavior (1969), Academic Press: Academic Press New York) · Zbl 0084.15504
[14] Estes, K. W., Learning Theory and Mental Development (1970), Academic Press: Academic Press New York
[15] Estes, K. W., Reinforcement in Human Behavior, Amer. Scientist, 60, 723-729 (1972)
[16] Estes, K. W.; Burke, C. J., A Theory of Stimulus Variability in Learning, Psychological Rev., 60, 276-286 (1953)
[17] Ethier, S. N.; Kurtz, T. G., Markov Processes. Characterization and Convergence (1985), Wiley: Wiley New York
[18] Guthrie, E. R., The Psychology of Learning (1952), Harper: Harper New York
[19] Harley, C. B., Learning the Evolutionarily Stable Strategy, J. Theoret. Biol., 89, 611-633 (1981)
[20] Herrnstein, R. J., On the Law of Effect, J. Experimental Anal. Behavior, 13, 243-266 (1970)
[21] Hofbauer, J.; Sigmund, K., The Theory of Evolution and Dynamical Systems. The Theory of Evolution and Dynamical Systems, Student Texts, 7 (1988), London Mathematical Society: London Mathematical Society London · Zbl 0678.92010
[22] Iosifescu, M.; Grigorescu, S., Dependence with Complete Connections and its Applications (1990), Cambridge Univ. Press: Cambridge Univ. Press Cambridge · Zbl 0749.60067
[23] Iosifescu, M.; Teodorescu, R., Random Processes and Learning (1969), Springer-Verlag: Springer-Verlag Berlin/New York · Zbl 0194.51101
[24] Kurtz, T. G., Approximation of Population Processes. Approximation of Population Processes, CBMS-NSF, Regional Conference Series in Applied Mathematics, SIAM (1981), SIAM: SIAM Philadelphia · Zbl 0465.60078
[25] Lettau, M.; Uhlig, H., Rules of Thumb and Dynamic Programming (1996), Tilburg UniversityCentER DP
[26] Ljung, L., Strong Convergence of Stochastic Approximation Algorithm, Ann. Statist., 6, 680-696 (1978) · Zbl 0402.62060
[27] Marimon, R. 1996, Learning from Learning Models, 1996 Congress of the Econometric Society.; Marimon, R. 1996, Learning from Learning Models, 1996 Congress of the Econometric Society.
[28] Maynard Smith, J., Evolution and the Theory of Games (1981), Cambridge Univ. Press: Cambridge Univ. Press Cambridge
[29] Norman, M. F., Markov Processes and Learning Models (1972), Academic Press: Academic Press New York · Zbl 0262.92003
[30] Rescorla, R. A., A Pavlovian Conditioning and Its Proper Control Procedures, Psychological Rev., 74, 71-80 (1967)
[31] Roth, A. E.; Erev, I., Learning in Extensive-Form Games: Experimental Data and Simple Dynamic Models in the Intermediate Term, Games Econ. Behavior, 8, 164-212 (1995) · Zbl 0833.90144
[32] Rustichini, A. 1998, Sophisticated Players and Sophisticated Agents, CentER Discussion Paper, Tilburg University.; Rustichini, A. 1998, Sophisticated Players and Sophisticated Agents, CentER Discussion Paper, Tilburg University.
[33] Shimp, C. P., Probabilistically Reinforced Choice Behavior in Pigeons, J. Experimental Anal. Behavior, 9, 443-455 (1966)
[34] Staddon, J. E.R., Learning as Adaptation, (Estes, W. K., Handbook of Learning and Cognitive Processes, Conditioning and Behavior Theory (1975), Wiley: Wiley New York)
[35] Tholman, E. C.; Honzik, C. H., Introduction and Removal of Reward and Maze Learning in Rats, Univ. California Publ. Psychology, 4, 257-275 (1930)
[36] Thorndike, E. L., Animal Intelligence: An Experimental Study of the Associative Processes in Animals, Psychological Rev., Monograph Suppl., 2 (1898)
[37] Thorndike, E. L., The Psychology of Wants. Interests and Attitudes (1935), Appleton-Century: Appleton-Century New York
[38] Watson, J., Behaviorism (1924), Norton: Norton New York
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.