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

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹ️ Information

Optimal Reinforcement Learning for Gaussian Systems

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Webinar - link in abstract Average on Sundays: 7253.98333333 kWh The Yusuf Hamied Theatre, Christ's College, Cambridge

Other talks

Title to be confirmed TBC Packing the Border: Quail Crates and the Regulation of Animal Movement on the US-Mexico Border, 1910s-1940s The concept of fitness in evolutionary biology: a philosophical analysis Decoding genomic chaos - a pancancer compendium of chromosomal instability The organisational management of traumatic stress
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity