University of Cambridge > Talks.cam > Machine Learning @ CUED > Optimal Reinforcement Learning for Gaussian Systems

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Optimal Reinforcement Learning for Gaussian Systems

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

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

The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. In this talk I will show that, however, if all beliefs are Gaussian processes, it is possible to make analytic statements about optimal learning of both rewards and transition dynamics, for nonlinear, time-varying systems in continuous time and space, subject to a relatively weak restriction on the dynamics: The solution is described by an infinite-dimensional partial differential equation. An approximate finite-dimensional projection provides a first impression for how this result may be helpful.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Danby Society david brailsford Topics in theoretical and experimental semantics and pragmatics (PhD course)

Other talks

The Partition of India and Migration Biopolymers for photonics - painting opals with water and light Single Molecule Spectroscopy Succulents with Altitude Methane and the Paris Agreement Dynamics of Phenotypic and Genomic Evolution in a Long-Term Experiment with E. coli Mathematical applications of little string theory An approach to the four colour theorem via Donaldson- Floer theory BP KEYNOTE LECTURE: Importance of C-O Bond Activation for CO2/COUtilization - An Approach to Energy Conversion and Storage Inferring the Evolutionary History of Cancers: Statistical Methods and Applications A rose by any other name Cosmology from the Kilo-Degree Survey
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity