Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Hao, Xiaotian"'
Multi-agent systems require effective coordination between groups and individuals to achieve common goals. However, current multi-agent reinforcement learning (MARL) methods primarily focus on improving individual policies and do not adequately addre
Externí odkaz:
http://arxiv.org/abs/2307.15530
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Autor:
Li, Pengyi, Tang, Hongyao, Yang, Tianpei, Hao, Xiaotian, Sang, Tong, Zheng, Yan, Hao, Jianye, Taylor, Matthew E., Tao, Wenyuan, Wang, Zhen, Barez, Fazl
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterized by Mutual Information (MI) in different forms.
Externí odkaz:
http://arxiv.org/abs/2203.08553
Autor:
Hao, Xiaotian, Mao, Hangyu, Wang, Weixun, Yang, Yaodong, Li, Dong, Zheng, Yan, Wang, Zhen, Hao, Jianye
The state space in Multiagent Reinforcement Learning (MARL) grows exponentially with the agent number. Such a curse of dimensionality results in poor scalability and low sample efficiency, inhibiting MARL for decades. To break this curse, we propose
Externí odkaz:
http://arxiv.org/abs/2203.05285
Autor:
Xian, Chunxing, Liu, Yanwu, Zhou, Lei, Ding, Ting, Chen, Jingdi, Wang, Taoran, Gao, Jiakai, Hao, Xiaotian, Bi, Long
Publikováno v:
In Journal of Infection and Chemotherapy December 2024 30(12):1237-1243
Autor:
Mao, Hangyu, Wang, Chao, Hao, Xiaotian, Mao, Yihuan, Lu, Yiming, Wu, Chengjie, Hao, Jianye, Li, Dong, Tang, Pingzhong
The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the com
Externí odkaz:
http://arxiv.org/abs/2111.08857
Autor:
Guss, William Hebgen, Milani, Stephanie, Topin, Nicholay, Houghton, Brandon, Mohanty, Sharada, Melnik, Andrew, Harter, Augustin, Buschmaas, Benoit, Jaster, Bjarne, Berganski, Christoph, Heitkamp, Dennis, Henning, Marko, Ritter, Helge, Wu, Chengjie, Hao, Xiaotian, Lu, Yiming, Mao, Hangyu, Mao, Yihuan, Wang, Chao, Opanowicz, Michal, Kanervisto, Anssi, Schraner, Yanick, Scheller, Christian, Zhou, Xiren, Liu, Lu, Nishio, Daichi, Tsuneda, Toi, Ramanauskas, Karolis, Juceviciute, Gabija
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Despite this, a majority of challenges suffer from the same fundamental pr
Externí odkaz:
http://arxiv.org/abs/2106.03748
Autor:
Chen, Jingdi, Wu, Wei, Xian, Chunxing, Wang, Taoran, Hao, Xiaotian, Chai, Na, Liu, Tao, Shang, Lei, Wang, Bo, Gao, Jiakai, Bi, Long
Publikováno v:
In Heliyon 15 April 2024 10(7)
Autor:
Hao, Xiaotian, Peng, Zhaoqing, Ma, Yi, Wang, Guan, Jin, Junqi, Hao, Jianye, Chen, Shan, Bai, Rongquan, Xie, Mingzhou, Xu, Miao, Zheng, Zhenzhe, Yu, Chuan, Li, Han, Xu, Jian, Gai, Kun
In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser's cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) u
Externí odkaz:
http://arxiv.org/abs/2006.16312
Autor:
Hao, Xiaotian, Jin, Junqi, Hao, Jianye, Li, Jin, Wang, Weixun, Ma, Yi, Zheng, Zhenzhe, Li, Han, Xu, Jian, Gai, Kun
Bipartite b-matching is fundamental in algorithm design, and has been widely applied into economic markets, labor markets, etc. These practical problems usually exhibit two distinct features: large-scale and dynamic, which requires the matching algor
Externí odkaz:
http://arxiv.org/abs/2005.04355
Many tasks in practice require the collaboration of multiple agents through reinforcement learning. In general, cooperative multiagent reinforcement learning algorithms can be classified into two paradigms: Joint Action Learners (JALs) and Independen
Externí odkaz:
http://arxiv.org/abs/1909.11468