Extended Replicator Dynamics as a Key to Reinforcement Learning in Multi-agent Systems

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning with Opponent-Learning Awareness (2017, methodology): “ouraged to deviate from the learning rule. The algorithm they propose applies to settings where all Nash equilibria can be computed and enumerated. At the intersection of RL and evolutionary methods, Tuyls et al. (2003) uses replicator dynamics for understanding the convergence points of multi-agent”
Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, methodology): “For instance, Tuyls et al. (2003) were the first to derive the selection-mutation dynamics of Q-learning in discrete-action normal-form games, and to visually compare traces of the learning algorithm with the predicted dynamics of the model.”
An Overview of Cooperative and Competitive Multiagent Learning (2005, methodology): “Another example is the Extended Replicator Dynamics algorithm of [174].”
An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games (2005, background): “In this section we will show the dynamics of Cross learning and Q-learning and illustrate them on different examples [40, 45, 48].”