University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Differentiable Planning

Differentiable Planning

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

If you have a question about this talk, please contact Robert Pinsler.

Planning is a key capability of intelligent agents for obtaining sequences of actions to achieve some goal. Recently, there have been several works that endow learning agents with the ability to plan by explicitly embedding a differentiable planner within a computation graph. The goal of this talk is to get an overview over these approaches under the theme of “differentiable planning” or “learning to plan”. This talk consists of two parts. First, we will give an introduction to planning, and how it relates to classic AI search as well as reinforcement learning. Second, we will motivate the idea behind differentiable planning and present some recent papers in more detail.

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity