Zobrazeno 1 - 10
of 304
pro vyhledávání: '"GUAN Cong"'
Publikováno v:
Dianzi Jishu Yingyong, Vol 49, Iss 3, Pp 61-66 (2023)
Abstract： With the increasing resolution of the input image of the current target detection task，the feature information extracted from the feature extraction network will become more and more limited under the condition that the receptive field
Externí odkaz:
https://doaj.org/article/b4e2b1049012475d8f5a681ac0d6fa4c
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this problem setti
Externí odkaz:
http://arxiv.org/abs/2411.10809
Autor:
Elena P. Krasovskaya, Guan Cong
Publikováno v:
Музыкальное искусство и образование, Vol 9, Iss 2, Pp 71-89 (2021)
The article addresses issues of the application of the polycontextual approach when students study the cycle “Romeo and Juliet” by S. Prokofiev in the piano class. This approach includes such important contexts as musical, literary, social, ide
Externí odkaz:
https://doaj.org/article/40880426c89c4c918de7d59182a2eeb6
Publikováno v:
Zhongguo Jianchuan Yanjiu, Vol 15, Iss 2, Pp 127-136 (2020)
Objectives Aiming at the influence of load fluctuation on the fuel cell life and power quality of a fuel cell hybrid ship, an energy management strategy based on real-time wavelet transform is proposed.Methods By the frequency division processing of
Externí odkaz:
https://doaj.org/article/e3f9cb2c57cf419d9ce491222e8d1e80
Quality-Diversity (QD) algorithms have emerged as a powerful optimization paradigm with the aim of generating a set of high-quality and diverse solutions. To achieve such a challenging goal, QD algorithms require maintaining a large archive and a lar
Externí odkaz:
http://arxiv.org/abs/2406.03731
Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are difficult for a s
Externí odkaz:
http://arxiv.org/abs/2312.01058
Autor:
Guan, Cong, Zhang, Lichao, Fan, Chunpeng, Li, Yichen, Chen, Feng, Li, Lihe, Tian, Yunjia, Yuan, Lei, Yu, Yang
Developing intelligent agents capable of seamless coordination with humans is a critical step towards achieving artificial general intelligence. Existing methods for human-AI coordination typically train an agent to coordinate with a diverse set of p
Externí odkaz:
http://arxiv.org/abs/2311.00416
Autor:
Yuan, Lei, Li, Lihe, Zhang, Ziqian, Chen, Feng, Zhang, Tianyi, Guan, Cong, Yu, Yang, Zhou, Zhi-Hua
In open multi-agent environments, the agents may encounter unexpected teammates. Classical multi-agent learning approaches train agents that can only coordinate with seen teammates. Recent studies attempted to generate diverse teammates to enhance th
Externí odkaz:
http://arxiv.org/abs/2309.12633
Autor:
Zhang, Ziqian, Yuan, Lei, Li, Lihe, Xue, Ke, Jia, Chengxing, Guan, Cong, Qian, Chao, Yu, Yang
In cooperative multi-agent reinforcement learning (MARL), where an agent coordinates with teammate(s) for a shared goal, it may sustain non-stationary caused by the policy change of teammates. Prior works mainly concentrate on the policy change durin
Externí odkaz:
http://arxiv.org/abs/2305.05911
Autor:
Yuan, Lei, Zhang, Zi-Qian, Xue, Ke, Yin, Hao, Chen, Feng, Guan, Cong, Li, Li-He, Qian, Chao, Yu, Yang
Cooperative multi-agent reinforcement learning (CMARL) has shown to be promising for many real-world applications. Previous works mainly focus on improving coordination ability via solving MARL-specific challenges (e.g., non-stationarity, credit assi
Externí odkaz:
http://arxiv.org/abs/2305.05909