Year: 2024
Type: conference-paper
Abstract: We create a novel benchmark for evaluating a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset, and propose a novel Scalable Lifelong Learning system capable of retaining knowledge from the previously learnt RL tasks. Our benchmark measures the efficacy of a deployable Life-long Learning system that is evaluated on scalability, performance and resource utilization. Our proposed system, once pretrained on the dataset, can be deployed to perform continual learning on unseen tasks. Our proposed method consists of a Few Shot Class Incremental Learning (FS-CIL) based task-mapper and an encoder/backbone trained entirely using the pretrain dataset. The policy parameters corresponding to the recognized task are then loaded to perform the task. We show that this system can be scaled to in-corporate a large number of tasks due to the small memory footprint and fewer computational resources. We perform experiments on our DeLL (Deployment for Lifelong Learning) benchmark on the Atari games to determine the efficacy of the system.
Authors: Kiran Lekkala, Eshan Bhargava, Laurent Itti
Institution: University of Southern California
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4394862557