Project Malmo

Microsoft's vision for gaming is a world where players are empowered to play the games they want, with the people they want, whenever they want, where-ever they are, and on any device. The Game Intelligence team, in close collaboration with…

The Reinforcement Learning research group works on theoretical foundations, algorithms, and systems for autonomous decision making. Our main research areas include exploration-exploitation trade-offs, off-policy learning, and generalization for contextual bandits, Markov decision processes, and contextual decision processes.