On the convergence of reinforcement learning

DOI10.1016/J.JET.2004.03.008zbMath1118.91025OpenAlexW2167425257MaRDI QIDQ1779805

A. W. Beggs

Publication date: 1 June 2005

Published in: Journal of Economic Theory (Search for Journal in Brave)

Full work available at URL: https://ora.ox.ac.uk/objects/uuid:97339c58-0d4c-40ca-a289-ce0e96fa04d6

zbMATH Keywords

GamesReinforcement learning

Mathematics Subject Classification ID

Noncooperative games (91A10) 2-person games (91A05) Rationality and learning in game theory (91A26)

Related Items (54)

Reference points and learning ⋮ Stochastic approximation to understand simple simulation models ⋮ A numerical analysis of the evolutionary stability of learning rules ⋮ A note on adjusted replicator dynamics in iterated games ⋮ State-policy dynamics in evolutionary games ⋮ Comparing human behavior models in repeated Stackelberg security games: an extended study ⋮ Evolutionary game theory: a renaissance ⋮ Wisdom of crowds versus groupthink: learning in groups and in isolation ⋮ Distributed dynamic reinforcement of efficient outcomes in multiagent coordination and network formation ⋮ An adaptive learning model with foregone payoff information ⋮ Learning in experimental \(2\times 2\) games ⋮ Evolutionary explanations of indicatives and imperatives ⋮ A functional equation whose unknown is \(\mathcal{P}([0,1)\) valued] ⋮ Learning in rent-seeking contests with payoff risk and foregone payoff information ⋮ Some dynamics of signaling games ⋮ Compositional signaling in a complex world ⋮ Immigrated urn models-theoretical properties and applications ⋮ Probe and adjust in information transfer games ⋮ Learning strict Nash equilibria through reinforcement ⋮ On the impulse in impulse learning ⋮ Convergence in models with bounded expected relative hazard rates ⋮ Statistical properties of two-color randomly reinforced urn design targeting fixed allocations ⋮ Transient and asymptotic dynamics of reinforcement learning in games ⋮ Emergence of information transfer by inductive learning ⋮ Nonconvergence to saddle boundary points under perturbed reinforcement learning ⋮ Evolutionary models of color categorization based on discrimination ⋮ On a notion of partially conditionally identically distributed sequences ⋮ Nonparametric covariate-adjusted response-adaptive design based on a functional urn model ⋮ Searching for information ⋮ Generalized reinforcement learning in perfect-information games ⋮ From imitation to collusion: long-run learning in a low-information environment ⋮ Asymptotic Properties of Multicolor Randomly Reinforced Pólya Urns ⋮ Network formation by reinforcement learning: the long and medium run ⋮ An urn model to construct an efficient test procedure for response adaptive designs ⋮ A randomly reinforced urn ⋮ Asymptotic theorems of sequential estimation-adjusted urn models ⋮ A payoff-based learning procedure and its application to traffic games ⋮ Generalised weakened fictitious play ⋮ Evolutionary game dynamics ⋮ On the learning patterns and adaptive behavior of terrorist organizations ⋮ Securing infrastructure facilities: when does proactive defense help? ⋮ Signaling Games ⋮ On salience and signaling in sender-receiver games: partial pooling, learning, and focal points ⋮ Convergence results on stochastic adaptive learning ⋮ Reinforcement with Fading Memories ⋮ Asymptotics in response-adaptive designs generated by a two-color, randomly reinforced urn ⋮ A central limit theorem, and related results, for a two-color randomly reinforced urn ⋮ Learning in Games via Reinforcement and Regularization ⋮ An Adjusted Payoff-Based Procedure for Normal Form Games ⋮ On the stability of an adaptive learning dynamics in traffic games ⋮ Interim analysis of clinical trials based on urn models ⋮ Infinite-color randomly reinforced urns with dominant colors ⋮ Equilibrium routing under uncertainty ⋮ An adaptive learning model in coordination games

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A behavioral learning process in games
• Nonconvergence to unstable points in urn models and stochastic approximations
• A strong law for some generalized urn processes
• Learning through reinforcement and replicator dynamics
• Vertex-reinforced random walk on \(\mathbb Z\) has finite range
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Optimal properties of stimulus-response learning models.
• Learning to be imperfect: The ultimatum game
• Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term
• Stochastic algorithms
• Do stochastic algorithms avoid traps?
• Adaptive Learning with Nonlinear Dynamics Driven by Dependent Processes
• Convergence Rate of Stochastic Approximation Algorithms in the Degenerate Case
• A dynamic model of social network formation
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
• Experience-weighted Attraction Learning in Normal Form Games
• Two Competing Models of How People Learn in Games
• Bernard Friedman's Urn
• A general class of adaptive strategies

This page was built for publication: On the convergence of reinforcement learning