MARL Sim2real Transfer: Merging Physical Reality With Digital Virtuality in Metaverse

Shi, Haoran; Liu, Guanjun; Zhang, Kaiwen; Zhou, Ziyuan; Wang, Jiacun

doi:10.1109/tsmc.2022.3229213

Cited by 18 publications

(8 citation statements)

References 54 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, various computational experiments considering human and social factors were conducted, evaluated, and shared with the real VCS system to improve its efficiency and robustness. Similar studies can be found in transportation systems [38], healthcare [39], education [40], and image encryption [41].…”

Section: Parallel Intelligent Systemssupporting

confidence: 68%

MetaEdu: a new framework for future education

Cui

Zhu

Hare

et al. 2023

Discov Artif Intell

View full text Add to dashboard Cite

The potential of the metaverse in the field of education is an area of increasing interest, with many researchers exploring the space to increase the ease and efficacy of student education while reducing time and labor requirements to deliver effective teaching. However, there has been little work into the systematic and technological aspects of delivering education through the metaverse. To fill this gap, we propose a metaverse education system that takes good advantages of virtual reality and Web3 blockchain techologies to create a social learning environment. With this added emphasis on social aspects, learners are able to socialize and engage in collaborative efforts to improve their own knowledge. Using blockchain technology, the system can also help to ensure security and transparency while also keeping progression and grading fair for all participating students.

show abstract

Section: Parallel Intelligent Systemssupporting

confidence: 68%

MetaEdu: a new framework for future education

Cui

Zhu

Hare

et al. 2023

Discov Artif Intell

View full text Add to dashboard Cite

show abstract

“…They defined the spectrum resource allocation problem as a discrete Markov decision process, and developed a quantum-inspired reinforcement learning mechanism to optimize the distributed vehicle selection policy. Shi et al [32] employed multi-agent reinforcement learning scheme to model the collective intelligence in digital entity, aiming to enhance the immersive environment in Metaverse. They implemented a deep deterministic policy gradient for the domain randomization, which could assist a perception-control modularization for the improvement of generalization performance in multiple unmanned aerial vehicle systems.…”

Section: Metaverse Applicationsmentioning

confidence: 99%

Personalized Federated Learning With Model-Contrastive Learning for Multi-Modal User Modeling in Human-Centric Metaverse

Zhou,

Yang,

Zheng

et al. 2024

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

With the flourish of digital technologies and rapid development of 5G and beyond networks, Metaverse has become an increasingly hotly discussed topic, which offers users with multiple roles for diversified experience interacting with virtual services. How to capture and model users' multi-platform or cross-space data/behaviors become essential to enrich people with more realistic and immersed experience in Metaverseenabled smart applications over 5G and beyond networks. In this study, we propose a Personalized Federated Learning with Model-Contrastive Learning (PFL-MCL) framework, which may efficiently enhance the communication and interaction in humancentric Metaverse environments by making use of the largescale, heterogeneous, and multi-modal Metaverse data. Differing from the conventional Federated Learning (FL) architecture, a multi-center aggregation structure to learn multiple global models based on the changes of dynamically updated local model weights, is developed in global, while a hierarchical neural network structure which includes a personalized module and a federated module to tackle both issues on data heterogeneity and model heterogeneity, is designed in local, so as to enhance the performance of PFL with unique characteristics of Metaverse data. In particular, a two-stage iterative clustering algorithm with a more precise initialization is developed to facilitate the personalized global aggregation with dynamically updated multiple aggregation centers. A personalized multi-modal fusion network is constructed to greatly reduce the computational cost and feature dimensions from the high-dimensional heterogeneous inputs for more efficient cross-modal fusion, based on a hierarchical shift-window attention mechanism and a newly designed bridge attention mechanism. A MCL scheme is then incorporated to speed up the model convergence with less communication

show abstract

“…Falchuk et al analyzes privacy in the social metaverse. The article raises concerns about users' privacy in shared virtual environments and highlights the im-portance of addressing privacy challenges to ensure a secure experience in the metaverse (Shi, G, 2023).…”

Section: B Security and Privacy In The Metaversementioning

confidence: 99%

Information Security in the Metaverse: A Systematic and Prospective Review

Mendoza Catagua,

Veloz Zambrano,

Alcívar Cedeño

et al. 2023

COCIRI

View full text Add to dashboard Cite

The Metaverse, a constantly evolving three-dimensional virtual space, has captured the attention of users eager for immersive experiences. However, this exciting digital world has also raised significant concerns regarding information security. This study delves into the extensive academic literature to conduct a comprehensive analysis of security tools in the Metaverse and explore future applications in this emerging context. Three key trends emerge from this in-depth analysis. Firstly, authentication and authorization stand out as cornerstones in protecting users and their data in the Metaverse. The increasing adoption of multifactor authentication underscores the importance of safeguarding access to this virtual environment. Additionally, end-to-end encryption is presented as a vital shield against potential data breaches. The second trend focuses on data protection and privacy. The concern for preserving the integrity of personal information drives the development and implementation of data anonymization technologies, marking a significant advancement in ensuring user privacy. The third trend relates to threat detection and response. In response to the growing sophistication of risks in the Metaverse, there is an observed increase in the adoption of artificial intelligence and machine learning technologies. These advanced tools play a crucial role in identifying and proactively mitigating security risks. In summary, this analysis reveals a dynamic landscape of security in the Metaverse, characterized by the constant evolution of tools and strategies to safeguard information. As this virtual environment continues to expand, information security emerges as a fundamental component to ensure immersive and secure digital experiences.

show abstract

MARL Sim2real Transfer: Merging Physical Reality With Digital Virtuality in Metaverse

Cited by 18 publications

References 54 publications

MetaEdu: a new framework for future education

MetaEdu: a new framework for future education

Personalized Federated Learning With Model-Contrastive Learning for Multi-Modal User Modeling in Human-Centric Metaverse

Information Security in the Metaverse: A Systematic and Prospective Review

Contact Info

Product

Resources

About