Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)ar...
详细信息
Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.
Editorial Photonics technology remains a driving force in today’s scientific landscape,marked by continuous innovation and crossdisciplinary *** an enlighting conversation with Light:science&Applications,*** May ...
详细信息
Editorial Photonics technology remains a driving force in today’s scientific landscape,marked by continuous innovation and crossdisciplinary *** an enlighting conversation with Light:science&Applications,*** May Lau,a pioneer in photonics research,shares her deep insights on the evolution of technologies of LEDs,lasers,challenges of hetero-epitaxy,and the future of micro-LEDs and quantum dot *** honored as a member of the US National Academy of engineering(NAE)for her significant contributions to photonics and electronics using III-V semiconductors on silicon,*** stands out as the sole Hong Kong scholar inducted into the NAE this year,joining 114 new and 21 international *** this exclusive Light People interview,*** shares her journey as a pioneering woman in engineering,her commitment to mentorship and academia,and her perspective on advancing female representation in *** summary provided is distilled from ***’s thoughtful responses during the *** a deeper exploration of ***’s experiences and advice,the full interview is available in the Supplementary material.
MXene is a promising energy storage material for miniaturized microbatteries and microsupercapacitors(MSCs).Despite its superior electrochemical performance,only a few studies have reported MXene-based ultrahigh-rate(...
详细信息
MXene is a promising energy storage material for miniaturized microbatteries and microsupercapacitors(MSCs).Despite its superior electrochemical performance,only a few studies have reported MXene-based ultrahigh-rate(>1000 mV s^(−1))on-paper MSCs,mainly due to the reduced electrical conductance of MXene films deposited on ***,ultrahigh-rate metal-free on-paper MSCs based on heterogeneous MXene/poly(3,4-ethylenedioxythiophene)-poly(styrenesulfonate)(PEDOT:PSS)-stack electrodes are fabricated through the combination of direct ink writing and femtosecond laser *** a footprint area of only 20 mm^(2),the on-paper MSCs exhibit excellent high-rate capacitive behavior with an areal capacitance of 5.7 mF cm^(−2)and long cycle life(>95%capacitance retention after 10,000 cycles)at a high scan rate of 1000 mV s^(−1),outperforming most of the present on-paper ***,the heterogeneous MXene/PEDOT:PSS electrodes can interconnect individual MSCs into metal-free on-paper MSC arrays,which can also be simultaneously charged/discharged at 1000 mV s^(−1),showing scalable capacitive *** heterogeneous MXene/PEDOT:PSS stacks are a promising electrode structure for on-paper MSCs to serve as ultrafast miniaturized energy storage components for emerging paper electronics.
In this edition of Light People,we are excited to feature *** Dai(Zhejiang University),*** Su(Shanghai Jiao Tong University),and *** Lo(Advanced Micro Foundry Pte Ltd,Singapore),three prominent researchers shaping the...
详细信息
In this edition of Light People,we are excited to feature *** Dai(Zhejiang University),*** Su(Shanghai Jiao Tong University),and *** Lo(Advanced Micro Foundry Pte Ltd,Singapore),three prominent researchers shaping the future of silicon *** collaborative work addresses critical issues in silicon photonics,including reducing propagation losses,enlarging the functionalities and enhancing building blocks,integrating efficient laser sources,expanding applications,and pushing the boundaries of optical and electronic *** this interview,we delve into their academic journeys,challenges,and future visions,offering insights into the ongoing evolution of silicon photonics and its potential to transform *** a deeper exploration of their experiences and advice,the full interview is available in the Supplementary material.
The permanent magnet (PM) Vernier machines enhance torque density and decrease cogging torque compared to conventional permanent magnet synchronous motor. This paper presents a novel fractional-slot H-shaped PM Vernie...
详细信息
Background In recent years,the demand for interactive photorealistic three-dimensional(3D)environments has increased in various fields,including architecture,engineering,and ***,achieving a balance between the quality...
详细信息
Background In recent years,the demand for interactive photorealistic three-dimensional(3D)environments has increased in various fields,including architecture,engineering,and ***,achieving a balance between the quality and efficiency of high-performance 3D applications and virtual reality(VR)remains *** This study addresses this issue by revisiting and extending view interpolation for image-based rendering(IBR),which enables the exploration of spacious open environments in 3D and ***,we introduce multimorphing,a novel rendering method based on the spatial data structure of 2D image patches,called the image *** this approach,novel views can be rendered with up to six degrees of freedom using only a sparse set of *** rendering process does not require 3D reconstruction of the geometry or per-pixel depth information,and all relevant data for the output are extracted from the local morphing cells of the image *** detection of parallax image regions during preprocessing reduces rendering artifacts by extrapolating image patches from adjacent cells in *** addition,a GPU-based solution was presented to resolve exposure inconsistencies within a dataset,enabling seamless transitions of brightness when moving between areas with varying light *** Experiments on multiple real-world and synthetic scenes demonstrate that the presented method achieves high"VR-compatible"frame rates,even on mid-range and legacy hardware,*** achieving adequate visual quality even for sparse datasets,it outperforms other IBR and current neural rendering *** Using the correspondence-based decomposition of input images into morphing cells of 2D image patches,multidimensional image morphing provides high-performance novel view generation,supporting open 3D and VR ***,the handling of morphing artifacts in the parallax image regions remains a topic for future resea
The security of digital images transmitted via the Internet or other public media is of the utmost *** encryption is a method of keeping an image secure while it travels across a non-secure communication medium where ...
详细信息
The security of digital images transmitted via the Internet or other public media is of the utmost *** encryption is a method of keeping an image secure while it travels across a non-secure communication medium where it could be intercepted by unauthorized *** study provides an approach to color image encryption that could find practical use in various *** proposed method,which combines four chaotic systems,employs singular value decomposition and a chaotic sequence,making it both secure and *** unified average change intensity,the number of pixels’change rate,information entropy analysis,correlation coefficient analysis,compression friendliness,and security against brute force,statistical analysis and differential attacks are all used to evaluate the algorithm’s *** a thorough investigation of the experimental data,it is concluded that the proposed image encryption approach is secure against a wide range of attacks and provides superior compression friendliness when compared to chaos-based alternatives.
With the rapid expansion of interactions across various domains such as knowledge graphs and social networks, anomaly detection in dynamic graphs has become increasingly critical for mitigating potential risks. Howeve...
详细信息
Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of vision large language models(VLLMs), existing visual instruction tuning datasets include the following limitations.(1...
详细信息
Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of vision large language models(VLLMs), existing visual instruction tuning datasets include the following limitations.(1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance,instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations.(2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and closer to real-world scenarios outputs. To address these challenges, we construct a high-quality, diverse visual instruction tuning dataset MMInstruct,which consists of 973k instructions from 24 domains. There are four instruction types: judgment, multiplechoice, long visual question answering, and short visual question answering. To construct MMInstruct, we propose an instruction generation data engine that leverages GPT-4V, GPT-3.5, and manual correction. Our instruction generation engine enables semi-automatic, low-cost, and multi-domain instruction generation at 1/6 the cost of manual construction. Through extensive experiment validation and ablation experiments,we demonstrate that MMInstruct could significantly improve the performance of VLLMs, e.g., the model fine-tuning on MMInstruct achieves new state-of-the-art performance on 10 out of 12 benchmarks. The code and data shall be available at https://***/yuecao0119/MMInstruct.
暂无评论