Evaluating Pretrained models for Deployable Lifelong Learning

Kiran Lekkala, Eshan Bhargava,Laurent Itti

2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)(2023)

引用 0|浏览3
暂无评分
摘要
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 Lifelong 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 (FSCIL) 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 incorporate 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.
更多
查看译文
关键词
Lifelong Learning,Scalable,Incremental Learning,Pre-training Dataset,Neural Network,Large Datasets,Feed-forward Network,Real-world Systems,Buffer Size,Types Of Games,Support Set,Robot Navigation,Number Of Games,Inductive Bias,Specific Game,Pre-training Phase,Catastrophic Forgetting,Specific Benchmark,Pre-trained Encoder
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要