Search

Your search keyword '"Liu, Shasha"' showing total 2,117 results
Start Over Author "Liu, Shasha"
2,117 results on '"Liu, Shasha"'

8. NeuronsMAE: A Novel Multi-Agent Reinforcement Learning Environment for Cooperative and Competitive Multi-Robot Tasks

Author

Hu, Guangzheng, Li, Haoran, Liu, Shasha, Ma, Mingjun, Zhu, Yuanheng, and Zhao, Dongbin

Subjects
Computer Science - Robotics
Abstract

Multi-agent reinforcement learning (MARL) has achieved remarkable success in various challenging problems. Meanwhile, more and more benchmarks have emerged and provided some standards to evaluate the algorithms in different fields. On the one hand, the virtual MARL environments lack knowledge of real-world tasks and actuator abilities, and on the other hand, the current task-specified multi-robot platform has poor support for the generality of multi-agent reinforcement learning algorithms and lacks support for transferring from simulation to the real environment. Bridging the gap between the virtual MARL environments and the real multi-robot platform becomes the key to promoting the practicability of MARL algorithms. This paper proposes a novel MARL environment for real multi-robot tasks named NeuronsMAE (Neurons Multi-Agent Environment). This environment supports cooperative and competitive multi-robot tasks and is configured with rich parameter interfaces to study the multi-agent policy transfer from simulation to reality. With this platform, we evaluate various popular MARL algorithms and build a new MARL benchmark for multi-robot tasks. We hope that this platform will facilitate the research and application of MARL algorithms for real robot tasks. Information about the benchmark and the open-source code will be released.

Published
2023

12. Machine Learning-Based User Scheduling in Integrated Satellite-HAPS-Ground Networks

Author

Dahrouj, Hayssam, Liu, Shasha, and Alouini, Mohamed-Slim

Subjects
Computer Science - Artificial Intelligence
Abstract

Integrated space-air-ground networks promise to offer a valuable solution space for empowering the sixth generation of communication networks (6G), particularly in the context of connecting the unconnected and ultraconnecting the connected. Such digital inclusion thrive makes resource management problems, especially those accounting for load-balancing considerations, of particular interest. The conventional model-based optimization methods, however, often fail to meet the real-time processing and quality-of-service needs, due to the high heterogeneity of the space-air-ground networks, and the typical complexity of the classical algorithms. Given the premises of artificial intelligence at automating wireless networks design and the large-scale heterogeneity of non-terrestrial networks, this paper focuses on showcasing the prospects of machine learning in the context of user scheduling in integrated space-air-ground communications. The paper first overviews the most relevant state-of-the art in the context of machine learning applications to the resource allocation problems, with a dedicated attention to space-air-ground networks. The paper then proposes, and shows the benefit of, one specific use case that uses ensembling deep neural networks for optimizing the user scheduling policies in integrated space-high altitude platform station (HAPS)-ground networks. Finally, the paper sheds light on the challenges and open issues that promise to spur the integration of machine learning in space-air-ground networks, namely, online HAPS power adaptation, learning-based channel sensing, data-driven multi-HAPSs resource management, and intelligent flying taxis-empowered systems., Comment: arXiv admin note: substantial text overlap with arXiv:2204.13257

Published
2022

13. Joint User Association and Beamforming in Integrated Satellite-HAPS-Ground Networks

Author

Liu, Shasha, Dahrouj, Hayssam, and Alouini, Mohamed-Slim

Subjects
Computer Science - Information Theory, Computer Science - Networking and Internet Architecture
Abstract

This paper proposes, and evaluates the benefit of, one particular hybrid satellite-HAPS-ground network, where one high-altitude-platform-station (HAPS) connected to one geo-satellite assists the ground base-stations (BSs) at serving ground-level users. The paper assumes that the geo-satellite is connected to the HAPS using free-space-optical backhaul link. The HAPS, equipped with multiple antennas, aims at transmitting the geo-satellite data to the users via radio-frequency (RF) links using spatial-multiplexing. Each ground BS, on the other hand, is equipped with multiple antennas, but directly serves the users through the RF links. The paper then focuses on maximizing the network-wide throughput, subject to HAPS payload connectivity constraint, HAPS and BSs power constraints, and backhaul constraints, so as to jointly determine the user association strategy of each user (i.e., user to geo-satellite via HAPS, or user to BS), and their associated beamforming vectors. We tackle such a mixed discrete-continuous optimization problem using an iterative approach, where the user association is determined using a combination of integer linear programming and generalized assignment problems, and where the beamforming strategy is found using a weighted-minimum-mean-squared-error approach. The simulations illustrate the appreciable gain of our proposed algorithm, and highlight the prospects of augmenting the ground networks with beamforming empowered HAPS for connecting the unconnected, and super-connecting the connected.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results