Reinforcement Learning in continuous state-spaces

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

• Philip Sterne (University of Cambridge)
• Monday 26 November 2007, 11:15-12:15
• TCM Seminar Room, Cavendish Laboratory, Department of Physics.

If you have a question about this talk, please contact Philip Sterne.

For this journal club I am interested in continuous state-space reinforcement learning. It is my gut feeling that if one makes enough simplifying assumptions then the problem becomes solvable (if computational concerns are ignored).

It would be great if everyone attending could spend some time thinking about which assumptions would make the solution easier (yet still interesting) and what form the various (intractable) integrals would have.

If you believe that Gaussian Processes might provide a good starting point for your thoughts, have a look at the following papers (though they are not essential if you have your own ideas)

• Bayes meets Bellman
• Reinforcement Learning with Gaussian Processes

There is also a relevant video lecture by Engel available here

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

This talk is included in these lists:

• Cambridge talks
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Interested Talks
• ML
• Machine Learning Journal Club
• Machine Learning Summary
• Quantum Matter Journal Club
• TCM Seminar Room, Cavendish Laboratory, Department of Physics
• TQS Journal Clubs
• rp587
• yk373's list

Note that ex-directory lists are not shown.