Abstract
In this paper we study learning procedures when counterfactuals (payoffs of not chosen actions) are not observed. The decision maker reasons in two steps: First, she updates her propensities for choosing each action after every payoff experience, where propensities can be interpreted as preferences. Then, she transforms these propensities into choice probabilities. We introduce a set of axioms on how propensities are updated and on how these propensities are translated into choices and study the decision marker's behavior when such axioms are in place. Our characterization includes the linear reinforcement learning rule from Roth and Erev (1995).
©2012 Walter de Gruyter GmbH & Co. KG, Berlin/Boston
Artikel in diesem Heft
- Advances Article
- Seller Cheap Talk in Almost Common Value Auction
- Strategic Effects of Renegotiation-Proof Contracts
- Contributions Article
- Uniquely Representing "A Preference for Uniformity"
- An Experimental Comparison of Sequential First- and Second-Price Auctions with Synergies
- Transparency, Career Concerns, and Incentives for Acquiring Expertise
- Career Concerns and Performance Reporting in Optimal Incentive Contracts
- Two Notes on the Blotto Game
- The Tennis Coach Problem: A Game-Theoretic and Experimental Study
- Multidimensional Product Differentiation with Discrete Characteristics
- Screening and Financial Contracting in the Face of Outside Competition
- On Rationalizability and Beliefs in Discrete Private-Value First-Price Auctions
- Commitment versus Flexibility in Enforcement Games
- Endogenous Preferences and Dynamic Contract Design
- Intergenerational Interactions in Human Capital Accumulation
- Behavior-Based Price Discrimination by a Patient Seller
- Altruism and Local Interaction
- Education Signaling with Uncertain Returns
- An Axiomatic Approach to Arbitration and its Application in Bargaining Games
- Consensual and Conflictual Democratization
- Topics Article
- Preference for Variety
- Information Theory and Observational Limitations in Decision Making
- Strict Concavity of the Value Function for a Family of Dynamic Accumulation Models
- A Folk Theorem for Games when Frequent Monitoring Decreases Noise
- Characterizing Welfare-egalitarian Mechanisms with Solidarity When Valuations are Private Information
- Correlation in the Multiplayer Electronic Mail Game
- Dominance Solvability of Large k-Price Auctions
- Treading a Fine Line: Characterisations and Impossibilities for Liberal Principles in Infinitely-Lived Societies
- An Axiomatization of Learning Rules when Counterfactuals are not Observed
- On a Notion of Similarity with Endowments in Public Economics
- Outsourcing and Downstream R&D under Economies of Scale
- On Communication and the Weak Sequential Core
- Asymmetric Single-peaked Preferences
- Revealing Private Information in Bargaining
Artikel in diesem Heft
- Advances Article
- Seller Cheap Talk in Almost Common Value Auction
- Strategic Effects of Renegotiation-Proof Contracts
- Contributions Article
- Uniquely Representing "A Preference for Uniformity"
- An Experimental Comparison of Sequential First- and Second-Price Auctions with Synergies
- Transparency, Career Concerns, and Incentives for Acquiring Expertise
- Career Concerns and Performance Reporting in Optimal Incentive Contracts
- Two Notes on the Blotto Game
- The Tennis Coach Problem: A Game-Theoretic and Experimental Study
- Multidimensional Product Differentiation with Discrete Characteristics
- Screening and Financial Contracting in the Face of Outside Competition
- On Rationalizability and Beliefs in Discrete Private-Value First-Price Auctions
- Commitment versus Flexibility in Enforcement Games
- Endogenous Preferences and Dynamic Contract Design
- Intergenerational Interactions in Human Capital Accumulation
- Behavior-Based Price Discrimination by a Patient Seller
- Altruism and Local Interaction
- Education Signaling with Uncertain Returns
- An Axiomatic Approach to Arbitration and its Application in Bargaining Games
- Consensual and Conflictual Democratization
- Topics Article
- Preference for Variety
- Information Theory and Observational Limitations in Decision Making
- Strict Concavity of the Value Function for a Family of Dynamic Accumulation Models
- A Folk Theorem for Games when Frequent Monitoring Decreases Noise
- Characterizing Welfare-egalitarian Mechanisms with Solidarity When Valuations are Private Information
- Correlation in the Multiplayer Electronic Mail Game
- Dominance Solvability of Large k-Price Auctions
- Treading a Fine Line: Characterisations and Impossibilities for Liberal Principles in Infinitely-Lived Societies
- An Axiomatization of Learning Rules when Counterfactuals are not Observed
- On a Notion of Similarity with Endowments in Public Economics
- Outsourcing and Downstream R&D under Economies of Scale
- On Communication and the Weak Sequential Core
- Asymmetric Single-peaked Preferences
- Revealing Private Information in Bargaining