A miniaturized microstrip patch antenna using a three-dimensional (3-D) printed substrate is presented in this paper. To achieve miniaturization, a triangular prism substrate is proposed to replace conventional cuboid...
详细信息
Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributio...
详细信息
Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous space. However, previous works fail to exploit the score-based structure of diffusion models, and instead utilize a simple behavior cloning term to train the actor, limiting their ability in the actor-critic setting. In this paper, we present a theoretical framework linking the structure of diffusion model policies to a learned Q-function, by linking the structure between the score of the policy to the action gradient of the Q-function. We focus on off-policy reinforcement learning and propose a new policy update method from this theory, which we denote Q-score matching. Notably, this algorithm only needs to differentiate through the denoising model rather than the entire diffusion model evaluation, and converged policies through Q-score matching are implicitly multi-modal and explorative in continuous domains. We conduct experiments in simulated environments to demonstrate the viability of our proposed method and compare to popular baselines. Source code is available from the project website: https://***/qsm. Copyright 2024 by the author(s)
A new multi-period transmission planning method is presented in this article to choose optimal solutions among the suggested HVAC and HVDC lines for installation in consecutive periods over a long-term planning horizo...
详细信息
This study uses quantum-inspired techniques to ad-dress the DC optimal power flow problem considering frequency constraints. Although numerous analytical and data-driven meth-ods have been developed to solve DC-OPF un...
详细信息
Loss functions are essential for optimizing the imaging performance of trained deep learning models. Thus, the design of tailored loss functions defines the effectiveness of deep learning imaging models. A loss functi...
详细信息
The cybersecurity of the power grid has gained increasing attraction in today's smart grid system. The dynamic load-altering attack (DLAA), which causes under-frequency trips by injecting an attacking load, and th...
详细信息
In recent years,exploring the relationship between community structure and node centrality in complex networks has gained significant attention from researchers,given its fundamental theoretical significance and pract...
详细信息
In recent years,exploring the relationship between community structure and node centrality in complex networks has gained significant attention from researchers,given its fundamental theoretical significance and practical *** address the impact of network communities on target nodes and effectively identify highly influential nodes with strong propagation capabilities,this paper proposes a novel influential spreaders identification algorithm based on density entropy and community structure(DECS).The proposed method initially integrates a community detection algorithm to obtain the community partition results of the *** then comprehensively considers the internal and external density entropies and degree centrality of the target node to evaluate its *** validation is conducted on eight networks of varying sizes through susceptible–infected–recovered(SIR)propagation experiments and network static attack *** experimental results demonstrate that the proposed method outperforms five other node centrality methods under the same comparative conditions,particularly in terms of information spreading capability,thereby enhancing the accurate identification of critical nodes in networks.
Optimizing the charging protocol for large-scale electric vehicles is complex and computationally costly. Therefore, this paper proposes an advanced approach using machine learning-assisted mean field game theory to h...
详细信息
Now Unmanned Aerial Vehicle (UAV) with Mobile Edge Computing (MEC) severs and Device-to-Device (D2D) communications provide offload computing services for User Devices (UDs). However, the UAV has relatively high trans...
详细信息
Traditional Convolutional Neural Networks have been successful in capturing local, position-invariant features in text, but their capacity to model complex transformation within language can be further explored. In th...
详细信息
暂无评论