Learning in Extensive-Form Games: Experimental Data and Simple Dynamic Models in the Intermediate Term*

By Alvin E. Roth, Ido Erev. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Multi-Agent Cooperation and the Emergence of (Natural) Language (2016, background): “A major question in game theory is whether equilibrium actually occurs in a game as convergence in learning is not guaranteed (Fudenberg & Peysakhovich, 2014; Roth & Erev, 1995).”
THE DECISION MAKER MATTERS: INDIVIDUAL VERSUS GROUP BEHAVIOUR IN EXPERIMENTAL BEAUTY- (2005, unknown): “Reinforcement learning (see Roth and Erev, 1995) captures the basic insights from psychology that choices leading to good outcomes in the past are more frequently repeated in the future (law of effect; Thorndike, 1898) and that learning curves are relatively steep in early periods, but flattening…”
ERC: A Theory of Equity, Reciprocity, and Competition (2000, background): “Interestingly, ERC implies that the auction market game studied by Roth et al. (1991) (discussed in section 1) is sufficiently different from the Bertrand game to obtain competitive results independent of the number of buyers.”
Generalised weakened fictitious play (2006, background): “Recent attempts to examine such processes have focussed on a particular form of reinforcement learning (Roth and Erev, 1995).”
Agent-Based Models and Human Subject Experiments (2004, unknown): “Roth and Erev (1995) compare the performance of various versions of their reinforcement learning model with experimental data from three different sequential games: a market game, a best-shot/weakest link game and the ultimatum bargaining game; in all of these games, the unique subgame perfect equil”
A Survey of Collectives (2004, methodology): “More sophisticated versions of this work employ simple Bayesian learning algorithms, or re-inventions of some of the techniques of the RL community [190].”
Minimal Requirements for the Emergence of Learned Signaling (2014, methodology): “In addition, this representation is identical to the reinforcement learning of Roth and Erev (1995).”
The Economist as Engineer: Game Theory, Experimentation, and Computation as Tools for Design Economics (2002, unknown): “35 See, e.g., Roth and Erev (1995) and Erev and Roth (1998) for one train of thought in that”