Autonomy Talks - David Fridovich-Keil: Learning Mixed Strategies in Lifted Trajectory Games

Autonomy Talks - 10/05/2022

Speaker: Prof. David Fridovich-Keil, University of Texas at Austin

Title: Learning Mixed Strategies in Lifted Trajectory Games

Abstract: As autonomous systems become more widely deployed, their performance depends strongly upon interactions with human beings and other autonomous actors. This talk presents a game theoretic view, and focuses on a key technical challenge which emerges. That is, what is the right space of strategies to consider when competing with other agents? We shall discuss recent results to appear at this year’s RSS in which we see that, by jointly reasoning about continuous actions and mixing probabilities, agents can achieve superior performance in noncooperative games.
Check out the official webpage to know more: https://idsc.ethz.ch/research-frazzoli/autonomy-talks.html

Видео Autonomy Talks - David Fridovich-Keil: Learning Mixed Strategies in Lifted Trajectory Games канала Autonomy Talks