Cooperating with Machines

no code implementations • 17 Mar 2017 • Jacob W. Crandall, Mayada Oudah, Tennom, Fatimah Ishowo-Oloko, Sherief Abdallah, Jean-François Bonnefon, Manuel Cebrian, Azim Shariff, Michael A. Goodrich, Iyad Rahwan

Here, we combine a state-of-the-art machine-learning algorithm with novel mechanisms for generating and acting on signals to produce a new learning algorithm that cooperates with people and other machines at levels that rival human cooperation in a variety of two-player repeated stochastic games.

Common Sense Reasoning Face Recognition

A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics

no code implementations • 15 Jan 2014 • Sherief Abdallah, Victor Lesser

We analyze our algorithm in two-player-two-action games and show that symbolically proving WPLs convergence is difficult, because of the non-linear nature of WPLs dynamics, unlike previous MARL algorithms that had either linear or piece-wise-linear dynamics.

reinforcement-learning Reinforcement Learning (RL)