Barfuss, W. Potsdam Institute for Climate Impact Research and Cooperation Partners;
Donges, Jonathan Friedemann Potsdam Institute for Climate Impact Research;
Kurths, Jürgen Potsdam Institute for Climate Impact Research;
Barfuss, W., Donges, J. F., Kurths, J. (2019): Deterministic limit of temporal difference reinforcement learning for stochastic games. - Physical Review E, 99, 4, Art. 043305.https://doi.org/10.1103/PhysRevE.99.043305