Imperial College London > Talks@ee.imperial > Unifying task specification in reinforcement learning by Dr Martha White > Unifying task specification in reinforcement learning
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Unifying task specification in reinforcement learningAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Joan P O'Brien. This talk has been canceled/deleted Abstract Markov decision processes have long been the standard formalism for sequential decision-making within reinforcement learning. But, this is not the full story; in reality, there are specialized instances that require separate treatment, with the most notable being episodic and continuing problems. In this talk, I will discuss a generalization to the discount that enables a more unified formalism for these settings. I will discuss some advantages of this generalization, for specifying a broader class of policy evaluation questions and in terms of unifying the theoretical treatment of these different settings. Bio Martha White is an assistant professor of Computing Science at the University of Alberta. Previously she was an assistant professor in the School of Informatics and Computing at Indiana University in Bloomington, and received her PhD in Computing Science from the University of Alberta in 2015. Her primary research goal is to develop algorithms for autonomous agents learning from streams of data. She focuses on developing practical algorithms for reinforcement learning and representation learning. This talk is part of the Unifying task specification in reinforcement learning by Dr Martha White series. This talk is included in these lists:This talk is not included in any other list Note that ex-directory lists are not shown. |
Other listsType the title of a new list here talks@ee.imperialOther talksControl, Management, and Optimisation of Hybrid Proton Exchange Membrane Fuel Cell Systems |