Ian Osband
About
Ian Osband is a researcher in artificial intelligence, focusing on decision-making under uncertainty, particularly in reinforcement learning (RL). He is known for his work on efficient exploration strategies, notably through the development of randomized value functions, as detailed in his Ph.D. thesis, "Deep Exploration via Randomized Value Functions," which earned second place in the national Dantzig dissertation award . Osband completed his Ph.D. at Stanford University under the supervision of Benjamin Van Roy, following undergraduate studies in mathematics at Oxford University. He has held research positions at DeepMind and OpenAI, where he contributed to advancements in RL algorithms and their applications. His work has significantly influenced both theoretical and practical aspects of reinforcement learning, particularly in the areas of exploration and uncertainty estimation. Read more