Nonconvergence to saddle boundary points under perturbed reinforcement learning

DOI10.1007/s00182-014-0449-3zbMath1388.91060OpenAlexW2051130642MaRDI QIDQ495761

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

Publication date: 15 September 2015

Published in: International Journal of Game Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00182-014-0449-3

zbMATH Keywords

replicator dynamicsreinforcement learninglearning in games

Mathematics Subject Classification ID

Noncooperative games (91A10) Rationality and learning in game theory (91A26) Evolutionary games (91A22)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed dynamic reinforcement of efficient outcomes in multiagent coordination and network formation
• Nonconvergence to unstable points in urn models and stochastic approximations
• Learning through reinforcement and replicator dynamics
• On the convergence of reinforcement learning
• Potential games
• On the linear model with two absorbing barriers
• A class of games possessing pure-strategy Nash equilibria
• Asymptotics of a matrix valued Markov chain arising in sociology.
• Attainability of boundary points under reinforcement learning
• Learning aspiration in repeated games
• Evolutionary Games and Population Dynamics
• A dynamic model of social network formation
• Learning Automata - A Survey
• Evolution with State-Dependent Mutations
• Maximally Stabilizing Task Release Control Policy for a Dynamical Queue
• Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria
• Potential games with continuous player sets

This page was built for publication: Nonconvergence to saddle boundary points under perturbed reinforcement learning