University of Cambridge > Talks.cam > Machine Learning @ CUED > General Reinforcement Learning

  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

General Reinforcement Learning

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

If you have a question about this talk, please contact Adrian Weller.

Reinforcement learning problems are often phrased in terms of Markov decision processes (MDPs). In this talk, we go beyond MDPs and consider reinforcement learning in environments that are non-Markovian, non-ergodic and only partially observable. Our focus will not be on practical algorithms, but rather on the fundamental underlying problems. How do we balance exploration and exploitation? How do we explore optimally? When is an agent optimal? We introduce the Bayesian agent AIXI , point out some of its problems, and discuss potential solutions.

Speaker: Jan Leike is a PhD student at the Australian National University working with Marcus Hutter.

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

Giving What We Can: Cambridge 2D and 3D Heterogeneous Photonic Integration for Future Information Systems - Professor S. J. Ben Yoo, University of California IfM Buns Talk J British Epigraphy Society Ibero-Romance Linguistics Seminars

Other talks

The Ethical and Legal Elements of Capacity and Consent Production Processes Group Seminar - 'Re-thinking biosensors for resource-limited settings' Undersampling in physical imaging inverse problems Holonomic D-modules, b-functions, and coadmissibility Large Scale Ubiquitous Data Sources for Crime Prediction
 

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