Michael Zauzigadded this to
Machine Learning and The Future

Deterministic limit of temporal difference reinforcement learning for stochastic games

aps.org - Wolfram Barfuss, Jonathan F. Donges, and Jürgen Kurths

Author(s): Wolfram Barfuss, Jonathan F. Donges, and Jürgen KurthsReinforcement learning is a way for an artificial intelligence system to learn by …

View on aps.org