University of Cambridge > Talks.cam > CUED Control Group Seminars > Machine learning based approaches for decision & control under uncertainties (in electric power systems)

Machine learning based approaches for decision & control under uncertainties (in electric power systems)

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

If you have a question about this talk, please contact Dr Guy-Bart Stan.

The talk will present two approaches for designing sequential decision strategies by exploiting ideas from supervised learning. The first one is a non-model based batch-mode reinforcement learning algorithm iteratively fitting Q-functions to a random sample of four-tuples (state, action, reward, next-state). The second one is a model based multi-stage stochastic programming algorithm extracting and aggregating optimized decisions computed over an ensemble of incomplete disturbance trees. The algorithms are motivated by and illustrated on electric power systems planning and control problems.

This talk is part of the CUED Control Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity