Formalizing Multi-state Learning Dynamics

Daniel Hennes, Karl Tuyls, Matthias Rauterberg
2008 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology  
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games. In previous work, we introduced piecewise replicator dynamics, a combination of replicators and piecewise models to account for multi-state problems. We formalize this promising proof of concept and provide definitions for the notion of average reward games, pure equilibrium cells and finally, piecewise replicator dynamics. These definitions are general in the number of
more » ... and states. Results show that piecewise replicator dynamics qualitatively approximate multi-agent reinforcement learning in stochastic games.
doi:10.1109/wiiat.2008.33 dblp:conf/iat/HennesTR08 fatcat:y4ohob5mrndnzatpjonvai3jly