State-Coupled Replicator Dynamics

This paper introduces a new model, i. e. state-coupled replicator dynamics, expanding the link between evolutionary game theory and multiagent reinforcement learning to multistate games. More precisely, it extends and improves previous work on piecewise replicator dynamics, a combination of replicators and piecewise models. The contributions of the paper are twofold. One, we identify and explain the major shortcomings of piecewise replicators, i. e. discontinuities and occurrences of qualitative anomalies. Two, this analysis leads to the proposal of the new model for learning dynamics in stochastic games, named state-coupled replicator dynamics. The preceding formalization of piecewise replicators general in the number of agents and states - is factored into the new approach. Finally, we deliver a comparative study of finite action-set learning automata to piecewise and state-coupled replicator dynamics. Results show that statecoupled replicators model learning dynamics in stochastic games more accurately than their predecessor, the piecewise approach.

Authors

• Daniel Hennes DeepMind
• Karl Tuyls University of Liverpool
• Matthias Rauterberg

Keywords

• Multi-agent learning
• Evolutionary game theory
• Replicator dynamics
• Stochastic games