University of Cambridge > Talks.cam > Applied and Computational Analysis > Multiply accelerated value iteration for affine fixed point problems and application to Markov decision processes

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹī¸ Information

Multiply accelerated value iteration for affine fixed point problems and application to Markov decision processes

Download to your calendar using vCal

If you have a question about this talk, please contact Hamza Fawzi .

We analyze a modified version of Nesterov accelerated gradient algorithm, which applies to affine fixed point problems with non self-adjoint matrices, such as the ones appearing in the theory of Markov decision processes with discounted or mean payoff criteria. We characterize the spectra of matrices for which this algorithm does converge with an accelerated asymptotic rate. We also introduce a dth-order algorithm, and show that it yields a multiply accelerated rate under more demanding conditions on the spectrum. We subsequently apply these methods to develop accelerated schemes for non-linear fixed point problems arising from Markov decision processes.

This talk is part of the Applied and Computational Analysis series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Biotechnology Seminar Series Annual Heritage Lecture Room C, West Hub

Other talks

Title to be confirmed The organisational management of traumatic stress Beyond Hubble: Studying the Earliest Galaxies with the James Webb Space Telescope "That's History. That's Truth. I Seen It Myself": T'tc~tsa (Wailaki) and the Enslavement of California Native Americans. Chemical strategies for biomolecule functionalisation, and biomaterial conjugation Cooperation as a Laboratory of Being
 

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