Sam Devlin
Principal Researcher
About
My long term goal is to create autonomous agents capable of intelligible decision making in a wide range of complex environments with real world applications. In particular, my passion is using digital games to push boundaries in the capabilities of modern AI and making state of the art methods accessible to encourage the creation of new ways to play. To achieve these goals, my research currently focuses on machine learning, artificial intelligence, digital games and player experience.
Featured content
Age of Empires IV: Machine Learning Trials and Tribulations at GDC 2022
At GDC 2022 we highlighted the technical challenges involved in integrating cutting edge RL research into a modern AAA game. This talk was a joint presentation between Microsoft ML researchers and the AI developers that worked on Age of Empires IV.
Project Paidia: a Microsoft Research & Ninja Theory Collaboration
One goal of Project Paidia, a collaborative research project, is to drive state of the art research in reinforcement learning to enable game agents that learn to collaborate with human players.
The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition
Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types. The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) competition is a new challenge that…