Curricular Robust Reinforcement Learning via GAN-Based Perturbation Through Continuously Scheduled Task Sequence
作者机构：Beijing Key Laboratory of Security and Privacy in Intelligent TransportationBeijing Jiaotong UniversityBeijing 100044China
出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)
年 卷 期：2023年第28卷第1期
页 面：27-38页
核心收录：
学科分类：0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学]
基 金：supported by the National Natural Science Foundation of China (Nos.61972025,61802389,61672092,U1811264,and 61966009) the National Key R&D Program of China (Nos.2020YFB1005604 and 2020YFB2103802)
主 题：robust reinforcement learning generative adversarial network(GAN)based model curricular learning
摘 要：Reinforcement learning(RL),one of three branches of machine learning,aims for autonomous learning and is now greatly driving the artificial intelligence development,especially in autonomous distributed systems,such as cooperative Boston Dynamics ***,robust RL has been a challenging problem of reliable aspects due to the gap between laboratory simulation and real *** efforts have been made to approach this problem,such as performing random environmental perturbations in the learning ***,one cannot guarantee to train with a positive perturbation as bad ones might bring failures to *** this work,we treat robust RL as a multi-task RL problem,and propose a curricular robust RL *** first present a generative adversarial network(GAN)based task generation model to iteratively output new tasks at the appropriate level of difficulty for the current ***,with these progressive tasks,we can realize curricular learning and finally obtain a robust *** experiments in multiple environments demonstrate that our method improves the training stability and is robust to differences in training/test conditions.
维普期刊数据库