Zobrazeno 1 - 10
of 5 421
pro vyhledávání: '"Zhou, Mi"'
Model-free algorithms are brought into the control system's research with the emergence of reinforcement learning algorithms. However, there are two practical challenges of reinforcement learning-based methods. First, learning by interacting with the
Externí odkaz:
http://arxiv.org/abs/2409.10722
Autor:
Wang, Canran, Wang, Jinwen, Zhou, Mi, Pham, Vinh, Hao, Senyue, Zhou, Chao, Zhang, Ning, Raviv, Netanel
The prevalence of 3D printing poses a significant risk to public safety, as any individual with internet access and a commodity printer is able to produce untraceable firearms, keys, counterfeit products, etc. To aid government authorities in combati
Externí odkaz:
http://arxiv.org/abs/2403.04918
This study analyzed images generated by three popular generative artificial intelligence (AI) tools - Midjourney, Stable Diffusion, and DALLE 2 - representing various occupations to investigate potential bias in AI generators. Our analysis revealed t
Externí odkaz:
http://arxiv.org/abs/2403.02726
Autor:
Zhou, Mi
Celebrity endorsement is a global billion-dollar business used by food, beverage and restaurant companies to influence dietary behaviors that may contribute to overweight and obesity. Evidence suggests that existing government policies and industry s
Externí odkaz:
http://hdl.handle.net/10919/105144
Adverse weather image restoration strives to recover clear images from those affected by various weather types, such as rain, haze, and snow. Each weather type calls for a tailored degradation removal approach due to its unique impact on images. Conv
Externí odkaz:
http://arxiv.org/abs/2312.05006
Finite Horizon Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems
Autor:
Zhou, Mi
In this article, the deep deterministic policy gradient (DDPG) method is used to learn an optimal control policy of a multi-region state-dependent switched system. We observe good performance of this model-free method and explain it in a rigorous mat
Externí odkaz:
http://arxiv.org/abs/2312.04767
Autor:
Zhou, Mi
Newton-Raphson controller is a powerful prediction-based variable gain integral controller. Basically, the classical model-based Newton-Raphson controller requires two elements: the prediction of the system output and the derivative of the predicted
Externí odkaz:
http://arxiv.org/abs/2309.17315
In this article, the optimal control problem for a harmonic oscillator with an inequality constraint is considered. The applied energy of the oscillator during a fixed final time period is used as the performance criterion. The analytical solution wi
Externí odkaz:
http://arxiv.org/abs/2309.16834
In this article, we consider the path-planning problem of a cooperative homogeneous robotic system with rigid formation. An optimal controller is designed for each agent in such rigid systems based on Pontryagin's minimum principle theory. We found t
Externí odkaz:
http://arxiv.org/abs/2309.08733
Autor:
Zhou, Mi
In this article, we consider a special operator called the two-dimensional rotation operator and analyze its convergence and finite-sample bounds under the $l_2$ norm and $l_\infty$ norm with constant step size. We then consider the same problem with
Externí odkaz:
http://arxiv.org/abs/2309.04867