Ian Osband
TalkRL: The Reinforcement Learning Podcast
00:00
Exploring Reinforcement Learning Concepts and Uncertainty
This chapter delves into the fundamental concepts of reinforcement learning, addressing challenges in exploration, delayed consequences, and uncertainty and the importance of handling epistemic uncertainty. It also discusses the speaker's journey from DeepMind to OpenAI, emphasizing the focus on scaling up machine learning methods and bridging Bayesian and deep learning approaches.
Transcript
Play full episode
