Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published May 24, 2017 | Version v1
Conference paper Open

Stochastic Stability Analysis of Perturbed Learning Automata with Constant Step-Size in Strategic-Form Games

  • 1. Software Competence Center Hagenberg GmbH

Description

This paper considers a class of reinforcement-learning that belongs to the family of Learning Automata and provides a stochastic-stability analysis in strategic-form games. For this class of dynamics, convergence to pure Nash equilibria has been demonstrated only for the fine class of potential games. Prior work primarily provides convergence properties of the dynamics through stochastic approximations, where the asymptotic behavior can be associated with the limit points of an ordinary-differential equation (ODE). However, analyzing global convergence through the ODE-approximation requires the existence of a Lyapunov or a potential function, which naturally restricts the applicability of these algorithms to a fine class of games. To overcome these limitations, this paper introduces an alternative framework for analyzing stochastic-stability that is based upon an explicit characterization of the (unique) invariant probability measure of the induced Markov chain.

Files

1702.08334.pdf

Files (238.6 kB)

Name Size Download all
md5:09e5a417d59424eec4c02e9f0ae4b8ac
238.6 kB Preview Download

Additional details

Funding

RePhrase – REfactoring Parallel Heterogeneous Resource-Aware Applications - a Software Engineering Approach 644235
European Commission