Ian Osband
TalkRL: The Reinforcement Learning Podcast
00:00
Introduction
The chapter delves into an interview with Dr. Ian Osband from OpenAI, exploring his groundbreaking work on decision-making under uncertainty in reinforcement learning. The conversation showcases Dr. Osband's innovative approaches like Bootstrap, DQN, and randomized value functions, demonstrating their impact on tackling epistemic uncertainty in RL and OpenAI's utilization of these solutions for exploration.
Transcript
Play full episode
