Zobrazeno 1 - 10
of 123
pro vyhledávání: '"Li, Boyao"'
Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-structured PGMs that correspon
Externí odkaz:
http://arxiv.org/abs/2305.17583
Publikováno v:
In Optics Communications 1 December 2024 572
Publikováno v:
In Scientia Horticulturae 1 January 2025 339
Publikováno v:
In Phytomedicine March 2024 125
Publikováno v:
2020 IEEE International Conference on Robotics and Automation (ICRA2020)
Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation
Externí odkaz:
http://arxiv.org/abs/2011.08027
Publikováno v:
In Finance Research Letters November 2023 57
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, whi
Externí odkaz:
http://arxiv.org/abs/1903.07854
Autor:
Li, Boyao, Wang, Xingjie, Liang, Yaoyao, Sun, Jinghua, Zhu, Sufang, Chen, Xiaoyong, Zhou, Guiyao
Publikováno v:
In Optics and Laser Technology June 2023 161