Learning to Control

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

• Dr Carl Edward Rasmussen (Department of Engineering, University of Cambridge)
• Friday 17 October 2008, 14:00-15:00
• Cambridge University Engineering Department, Lecture Room 3B.

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.

This talk is included in these lists:

• All Talks (aka the CURE list)
• CUED Control Group Seminars
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge University Engineering Department, Lecture Room 3B
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.