Reinforcement Learning

The Waymo Driver: The Most Advanced Real-World Application of AI

Abstract:

Autonomous vehicles are the most mature manifestation of AI in the physical world today. Waymo is now serving well over 150K paid public rides every week, without a human driver, across some of the most complex urban environments in the U.S., including San...
Operator World Models for Reinforcement Learning - Pietro Novelli

Abstract

Policy Mirror Descent is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning due to the inaccessibility of explicit action-value functions. We address this challenge by...
Logical Team Q-learning: An approach towards factored policies in cooperative MARL

Abstract

...
Natasha Alechina
Brian Logan
Chance-Constrained Control with Lexicographic Deep Reinforcement Learning
Networked Systems
Artificial Intelligence and Robotics