Distributed Lifelong Reinforcement Learning with Sub-Linear Regret

Date December 12, 2017
Authors Julia El-Zini, Rasul Tutunov, Haitham Bou-Ammar, Ali Jadbabaie

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.

View paper