Zobrazeno 1 - 10
of 30 697
pro vyhledávání: '"Hong Zhang"'
Reward shaping is a critical component in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. While shaping rewards have been introduced to provide additional guidance, selecting effective shaping fun
Externí odkaz:
http://arxiv.org/abs/2410.13837
The ability to efficiently explore high-dimensional state spaces is essential for the practical success of deep Reinforcement Learning (RL). This paper introduces a new exploration technique called Random Latent Exploration (RLE), that combines the s
Externí odkaz:
http://arxiv.org/abs/2407.13755
Publikováno v:
Reinforcement Learning Journal, vol. 4, 2024, pp. 1598-1618
Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance. However, few work
Externí odkaz:
http://arxiv.org/abs/2407.03995
Generating varied scenarios through simulation is crucial for training and evaluating safety-critical systems, such as autonomous vehicles. Yet, the task of modeling the trajectories of other vehicles to simulate diverse and meaningful close interact
Externí odkaz:
http://arxiv.org/abs/2406.04300
Autor:
Hong, Zhang-Wei, Shenfeld, Idan, Wang, Tsun-Hsuan, Chuang, Yung-Sung, Pareja, Aldo, Glass, James, Srivastava, Akash, Agrawal, Pulkit
Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted content, the current paradigm is to recruit a \textit{red team} of human
Externí odkaz:
http://arxiv.org/abs/2402.19464
Depth completion is a long-standing challenge in computer vision, where classification-based methods have made tremendous progress in recent years. However, most existing classification-based methods rely on pre-defined pixel-shared and discrete dept
Externí odkaz:
http://arxiv.org/abs/2402.13579
Deep reinforcement learning methods exhibit impressive performance on a range of tasks but still struggle on hard exploration tasks in large environments with sparse rewards. To address this, intrinsic rewards can be generated using forward model pre
Externí odkaz:
http://arxiv.org/abs/2310.17537
Autor:
Hong, Zhang-Wei, Kumar, Aviral, Karnik, Sathwik, Bhandwaldar, Abhishek, Srivastava, Akash, Pajarinen, Joni, Laroche, Romain, Gupta, Abhishek, Agrawal, Pulkit
Publikováno v:
NeurIPS 2023
Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning techniques s
Externí odkaz:
http://arxiv.org/abs/2310.04413
Autor:
Huaiya Xie, Yaqi Wang, Yan Xu, Luo Wang, Junping Fan, Siqi Pan, Chuan Shi, Xiaoyan Liu, Xiaoxing Gao, Xiaobei Guo, Siyuan Yu, Jia Liu, Dongming Zhang, Yanli Yang, Hong Zhang, Jinglan Wang, Aohua Wu, Xueqi Liu, Jihai Liu, Huadong Zhu, Xiang Zhou, Xinlun Tian, Mengzhao Wang
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-8 (2024)
Abstract The study was to evaluate the clinical outcomes of azvudine versus nirmatrelvir-ritonavir against omicron strains of coronavirus disease 2019 infections and determine their comparative effectiveness. This retrospective study included 716 pat
Externí odkaz:
https://doaj.org/article/d88b3e55da7d4fe7873f45189db8222e
Autor:
Xing Guo, Hao Wang, Meng Liu, Jin-Mei Xu, Ya-Nan Liu, Hong Zhang, Xin-Xin He, Jiang-Xian Wang, Wei Wei, Da-Long Ren, Run-Shen Jiang
Publikováno v:
Animal Bioscience, Vol 37, Iss 10, Pp 1673-1682 (2024)
Objective Increasing breast meat production is one of the primary goals of the broiler industry. Over the past few decades, tremendous progress has been made in genetic selection and the identification of candidate genes for improving the breast musc
Externí odkaz:
https://doaj.org/article/aca37a3404f14f4c9491a806866dc55f