Nonconvergence to saddle boundary points under perturbed reinforcement learning
- 11 September 2014
- journal article
- research article
- Published by Springer Nature in International Journal of Game Theory
- Vol. 44 (3) , 667-699
Abstract
No abstract availableKeywords
This publication has 22 references indexed in Scilit:
- Distributed Dynamic Reinforcement of Efficient Outcomes in Multiagent Coordination and Network FormationDynamic Games and Applications, 2011
- Evolutionary dynamics and potential games in non-cooperative routing2007
- Learning aspiration in repeated gamesJournal of Economic Theory, 2005
- On the convergence of reinforcement learningJournal of Economic Theory, 2005
- Asymptotics of a matrix valued Markov chain arising in sociologyStochastic Processes and their Applications, 2003
- Evolutionary Games and Population Dynamics1998
- Learning Through Reinforcement and Replicator DynamicsJournal of Economic Theory, 1997
- Evolution with State-Dependent MutationsEconometrica, 1996
- On designing economic agents that behave like human agentsJournal of Evolutionary Economics, 1993
- Stochastic models for learning.1955