Výsledky vyhledávání - "ZHANG Xuetao"

Report

MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning

Autor: Lei, Xing, Zhang, Xuetao, Wang, Donglin

Publikováno v: AAAI 2025

Recently, a state-of-the-art family of algorithms, known as Goal-Conditioned Weighted Supervised Learning (GCWSL) methods, has been introduced to tackle challenges in offline goal-conditioned reinforcement learning (RL). GCWSL optimizes a lower bound

Externí odkaz: http://arxiv.org/abs/2412.11410

Zobrazit plný text záznamu

Report

Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming

Autor: Lei, Xing, Zhang, Xuetao, Zhuang, Zifeng, Wang, Donglin

A novel class of advanced algorithms, termed Goal-Conditioned Weighted Supervised Learning (GCWSL), has recently emerged to tackle the challenges posed by sparse rewards in goal-conditioned reinforcement learning (RL). GCWSL consistently delivers str

Externí odkaz: http://arxiv.org/abs/2410.06648

Zobrazit plný text záznamu

Akademický článek

Multi-granularity Android malware fast detection based on opcode

Autor: ZHANG Xuetao, SUN Meng,WANG Jinshuang

Publikováno v: 网络与信息安全学报, Vol 5, Iss 6, Pp 85-94 (2019)

The detection method based on opcode is widely used in Android malware detection, but it still contains some problems such as complex feature extraction method and low efficiency. In order to solve these problems, a multi-granularity fast detection m

Externí odkaz: https://doaj.org/article/9c6d1cd39c314865b2b8a118229efd32