Zobrazeno 1 - 10
of 1 455
pro vyhledávání: '"Wang, Che"'
To enhance the intelligence degree in operation and maintenance, a novel method for fault detection in power grids is proposed. The proposed GNN-based approach first identifies fault nodes through a specialized feature extraction method coupled with
Externí odkaz:
http://arxiv.org/abs/2311.16522
In this paper, we propose a method for knowledge graph construction in power distribution networks. This method leverages entity features, which involve their semantic, phonetic, and syntactic characteristics, in both the knowledge graph of distribut
Externí odkaz:
http://arxiv.org/abs/2311.08724
Recently, it has been shown that for offline deep reinforcement learning (DRL), pre-training Decision Transformer with a large language corpus can improve downstream performance (Reid et al., 2022). A natural question to ask is whether this performan
Externí odkaz:
http://arxiv.org/abs/2310.00771
Autor:
He, Tairan, Zhang, Yuge, Ren, Kan, Liu, Minghuan, Wang, Che, Zhang, Weinan, Yang, Yuqing, Li, Dongsheng
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted objectives rely hea
Externí odkaz:
http://arxiv.org/abs/2210.06041
In reinforcement learning, Monte Carlo algorithms update the Q function by averaging the episodic returns. In the Monte Carlo UCB (MC-UCB) algorithm, the action taken in each state is the action that maximizes the Q function plus a UCB exploration te
Externí odkaz:
http://arxiv.org/abs/2209.02864
Autor:
Li, Qian1,2 (AUTHOR) 2200902166@cnu.edu.cn, Wang, Che1 (AUTHOR) 6697@cnu.edu.cn, An, Lu3,4 (AUTHOR) anlu2021@tongji.edu.cn, Ding, Minghu2,5 (AUTHOR)
Publikováno v:
Remote Sensing. May2024, Vol. 16 Issue 10, p1673. 20p.
We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major obstacles in taking a data-driven approach, and present a suite of design prin
Externí odkaz:
http://arxiv.org/abs/2202.10324
Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-th
Externí odkaz:
http://arxiv.org/abs/2111.09159
Publikováno v:
In International Journal of Mechanical Sciences 1 July 2024 273
Autor:
Ji, Chao, Liu, Silin, Wang, Che, Chen, Jie, Wang, Jin, Zhang, Xinyue, Ma, Jinlu, Cai, Mengjiao
Publikováno v:
In Cancer Pathogenesis and Therapy July 2024 2(3):180-186