University of Cambridge > Talks.cam > CUED Control Group Seminars > Learning to Control

Learning to Control

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

If you have a question about this talk, please contact Dr Guy-Bart Stan.

Learning from examples is a powerful paradigm for aquiring motor skills in biological (human) systems. In this talk I will examine the possibility of learning control in artificial systems using modern probabilistic models from machine learning. The focus of the talk will be the learning process itself, and I will demonstrate very fast learning from no prior knowledge in a cart and pole balancing problem. Technically, our approach is based on reinterpreting control as a problem of statistical inference, and we show that the proper, Bayesian, treatment of uncertainty is crucial to the success of the method.

The talk is based on on-going research in collaboration with Marc P. Deisenroth .

This talk is part of the CUED Control Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2018 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity