Professor Stone's research aims to enable multiple intelligent agents to learn to act both individually and in coordination with one another towards individual and/or common goals in real-time, noisy, collaborative and adversarial environments. His approach is to study complete agents in specific, complex environments, with the goal of drawing general lessons from the specific implementations. Past and current application domains include robotic soccer, autonomous bidding agents, and social agents; Artificial intelligence, multiagent systems, machine learning, multiagent learning, robotics, auctions.