Distributed Lifelong Reinforcement Learning with Sub-Linear Regret

back to our research

Distributed Lifelong Reinforcement Learning with Sub-Linear Regret

17-19 December 2018, Miami Beach

IEEE Conference on Decision and Control (CDC), Miami Beach, Dec. 17-19, 2018 (To Appear)

Authors: Julia El-Zini, Rasul Tutunov (PROWLER.io), Haitham Bou-Ammar (PROWLER.io), and Ali Jadbabaie

Abstract: In this paper, we propose a distributed second- order method for lifelong reinforcement learning (LRL). Upon observing a new task, our algorithm scales state-of-the-art LRL by approximating the Newton direction up-to-any arbitrary precision ε > 0, while guaranteeing accurate solutions. We analyze the theoretical properties of this new method and derive, for the first time to the best of our knowledge, sublinear regret under this setting

Distributed Optimisation

Learning to Learn

Lifelong Learning

Online Learning

Reinforcement Learning


See paper

Join us to make AI that will change the world

join our team