Scalable lifelong reinforcement learning. (December 2017)

• Record Type: Journal Article
• Authors: Zhan, Yusen; Ammar, Haitham Bou; Taylor, Matthew E.
• Is Part Of: Pattern recognition. Volume 72(2017:Dec.)
• Page Start: 407
• Page End: 418
• Publication Date: 2017-12
• Subjects: Reinforcement learning -- Lifelong learning -- Distributed optimization -- Transfer learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.07.031
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Deriving a novel scalable algorithm for lifelong policy search in reinforcement learning. Acquiring linear convergence rate of our new algorithm Demonstrating the effectiveness of our technique dynamical systems and learning speed-ups on unobserved tasks. Abstract: Lifelong reinforcement learning provides a successful framework for agents to learn multiple consecutive tasks sequentially. Current methods, however, suffer from scalability issues when the agent has to solve a large number of tasks. In this paper, we remedy the above drawbacks and propose a novel scalable technique for lifelong reinforcement learning. We derive an algorithm which assumes the availability of multiple processing units and computes shared repositories and local policies using only local information exchange. We then show an improvement to reach a linear convergence rate compared to current lifelong policy search methods. Finally, we evaluate our technique on a set of benchmark dynamical systems and demonstrate learning speed-ups and reduced running times.