Nonconvergence to Saddle Boundary Points under Perturbed Reinforcement Learning

Abstract

This paper presents a novel reinforcement learning algorithm and provides conditions for global convergence to Nash equilibria. For several classes of reinforcement learning schemes, including the ones proposed here, excluding convergence to action profiles which are not Nash equilibria may not be trivial, unless the step-size sequence is appropriately tailored to the specifics of the game. In this paper we sidestep these issues by introducing a perturbed reinforcement learning scheme where the strategy of each agent is perturbed by a strategy-dependent perturbation (or mutations) function. Contrary to prior work on equilibrium selection in games where perturbation functions are globally state dependent, the perturbation function here is assumed to be local, i.e., it only depends on the strategy of each agent. We provide conditions under which the strategies of the agents will converge to an arbitrarily small neighborhood of the set of Nash equilibria almost surely. This extends prior analysis on reinforcement learning in games which has been primarily focused on urn processes. We finally specialize the results to a class of potential games.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 07, 2012
Accession Number
ADA584441

Entities

People

  • Anders Rantzer
  • Georgios C. Chasparis
  • Jeff S. Shamma

Organizations

  • Georgia Tech

Tags

Communities of Interest

  • C4I
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Boundaries
  • Convergence
  • Dynamics
  • Learning
  • Markov Processes
  • Mutations
  • Perturbations
  • Probability
  • Probability Distributions
  • Random Variables
  • Reinforcement Learning
  • Sensitivity
  • Sequences
  • Social Sciences
  • Standards
  • Stochastic Processes

Fields of Study

  • Economics

Readers

  • Calculus or Mathematical Analysis
  • Game Theory.
  • Linear Algebra

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms