Neural networks as a unifying learning model for random normal form games

Authors:
Leonidas Spiliopoulos
Affiliations:
University of New South Wales, The Australian School of Business, School of Economics, New South Wales, Australia
Venue:
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Year:
2011

Citing 12
Cited 0

Adaptive pattern recognition and neural networks

Adaptive pattern recognition and neural networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
Neural network design and the complexity of learning

Neural network design and the complexity of learning
Approximation capabilities of multilayer feedforward networks

Neural Networks
Methods to speed up error back-propagation learning algorithm

ACM Computing Surveys (CSUR)
Local minima and plateaus in hierarchical structures of multilayer perceptions

Neural Networks
Stated choice methods: analysis and application

Stated choice methods: analysis and application
Case-Based Reasoning: Experiences, Lessons and Future Directions

Case-Based Reasoning: Experiences, Lessons and Future Directions
Handbook of Computational Economics

Handbook of Computational Economics
Agent-Based Computational Economics: Growing Economies From the Bottom Up

Artificial Life
Handbook of Computational Economics, Volume 2: Agent-Based Computational Economics (Handbook of Computational Economics)

Handbook of Computational Economics, Volume 2: Agent-Based Computational Economics (Handbook of Computational Economics)
A neural network model of cortical activity during reaching

Journal of Cognitive Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article models the learning process of a population of randomly rematched tabula rasa neural network agents playing randomly generated 3 脙聴 3 normal form games of all strategic types. Evidence was found of the endogenous emergence of a similarity measure of games based on the number and types of Nash equilibria, and of heuristics that have been found effective in describing human behavior in experimental one-shot games. The neural network agents were found to approximate experimental human behavior very well across various dimensions such as convergence to Nash equilibria, equilibrium selection, and adherence to principles of dominance and iterated dominance. This is corroborated by evidence from five studies of experimental one-shot games, because the Spearman correlation coefficients of the probability distribution over the neural networks' and human subjects' actions ranged from 0.49 to 0.89.