Videos of Presentations (that happen to be available)
- Reinforcement Learning in Artificial Intelligence: Learning, Planning and Knowledge Representation
A Tutorial at Neural Information Processing Systems (NIPS), Vancouver, 2005
- Reinforcement Learning: A Tutorial
at Machine Learning Summer School in Canberra, Australia, 2006
- Efficiently Learning Linear-Linear Exponential Family Predictive Representations of State
at International Conference on Machine Learning (ICML), 2008
- Rethinking Rewards in Reinforcement Learning (or Where do Rewards Come From?)
an audio-only with slides recording of a talk at the STIET seminar at the University of Michigan, Fall 2009
- Reinforcement Learning: A Tutorial + Rethinking State, Action and Reward
at Machine Learning Summer School in Sardinia, Italy, 2010