Normal view MARC view

Strategic learning and its limits

Author: Young, H. Peyton Publisher: Oxford University Press (OUP) 2004.Language: EnglishDescription: 165 p. : Graphs ; 23 cm.ISBN: 0199269181Type of document: BookNote: Essay based on the Arne Ryde Memorial Lectures 2002Bibliography/Index: Includes bibliographical references and index
Tags: No tags from this library for this title. Log in to add tags.
Item type Current location Collection Call number Status Date due Barcode Item holds
Book Europe Campus
Main Collection
Print HD6954.3 .Y68 2004
(Browse shelf)
001252552
Available 001252552
Total holds: 0

Essay based on the Arne Ryde Memorial Lectures 2002

Includes bibliographical references and index

Digitized

Strategic Learning and Its Limits Contents Acknowledgements 1. The Interactive Learning Problem 2. Reinforcement and Regret 2.1. Reinforcement learning 2.2. Learning in stationary environments 2.3. Criteria of performance 2.4. Regret 2.5. Regret matching 2.6. Realized payoffs 2.7. The logic of regret matching 3. Equilibrium 3.1. forms of equilibrium 3.2. Examples 3.3. A generalization of correlated equilibrium 3.4. Learning coarse correlated equilibrium 3.5. Concepts of convergence 4. Conditional No-Regret Learning 4.1. Conditional versus unconditional regret 4.2. Blackwell's approachability theorem 4.3. Eliminating conditional regret 4.4. Simple rules minimizing conditional regret 4.5. A generalization of Blackwell's Theorem 4.6. Summary 5. Prediction, Postdiction, and Calibration 5.1. Prediction of an unknown process 5.2. An impossibility theorem of Oakes 5.3. Random forecasting rules xi 1 10 10 16 18 19 21 22 25 29 29 32 34 36 39 43 43 45 51 54 57 60 62 62 64 68 5.4. Foster's forecasting rule 5.5. Calibrated forecasting and correlated equilibrium 6. Fictitious Play and Its Variants 6.1. Predictive learning rules 6.2. Smoothed fictitious play 6.3. Better versus best reply 6.4. Finite memory and inertia 6.5. Convergence for weakly acyclic games 7. Bayesian Learning 7.1. The inference problem 7.2. An example 7.3. Strategies and beliefs 7.4. Optimality and equilibrium 7.5. Uncertainty and robustness 7.6.' An impossibility theorem 7.7. Further implications 8. Hypothesis Testing 8.1. Cognitive learning theory 8.2. Cognitive learning in games 8.3. The structure of hypothesis testing 8.4. Naive hypothesis testing 8.5. Dynamics of hypothesis testing 8.6. Learning Nash equilibrium 8.7. Hypothesis testing: the general case 8.8. Models, hunches, and beliefs 8.9. Convergence in probability 8.10. Learning to predict 9. Conclusion References Index 72 74 76 76 80 83 84 86 91 91 92 95 99 103 106 110 113 113 114 116 119 122 129 131 137 139 142 144 149 159

There are no comments for this item.

Log in to your account to post a comment.
Koha 18.11 - INSEAD Catalogue
Home | Contact Us | What's Koha?