2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDMLSP-27.4
Paper Title KERNEL-BASED LIFELONG POLICY GRADIENT REINFORCEMENT LEARNING
Authors Rami Mowakeaa, Seung-Jun Kim, University of Maryland, Baltimore County, United States; Darren Emge, Combat Capabilities Development Command, United States
SessionMLSP-27: Reinforcement Learning 3
LocationGather.Town
Session Time:Thursday, 10 June, 13:00 - 13:45
Presentation Time:Thursday, 10 June, 13:00 - 13:45
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-REI] Reinforcement learning
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract Policy gradient methods have been widely used in reinforcement learning (RL), especially thanks to their facility to handle continuous state spaces, strong convergence guarantees, and low-complexity updates. Training of the methods for individual tasks, however, can still be taxing in terms of the earning speed and the sample trajectory collection. Lifelong learning aims to exploit the intrinsic structure shared among a suite of RL tasks, akin to multitask learning, but in an efficient online fashion. In this work, we propose a lifelong RL algorithm based on the kernel method to leverage nonlinear features of the data based on a popular union-of-subspace model. Experimental results on a set of simple related tasks verify the advantage of the proposed strategy, compared to the single-task and the parametric counterparts.