University of Cambridge > Talks.cam > Machine Learning Journal Club > Value Propagation: A Graphical Model for Bayesian Reinforcement Learning

Value Propagation: A Graphical Model for Bayesian Reinforcement Learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Carl Scheffler.

I will present Bayesian Reinforcement Learning methods based on the model-free approach used in the Temporal Difference family of algorithms. Our implementations allow for the incorporation of prior knowledge in a principled way and automatically adapt their learning rate and backup depth. In policy iteration settings, they can guide exploration and converge on the optimal policy in an automated fashion, because they track the uncertainty of evaluations.

This talk is part of the Machine Learning Journal Club series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity