Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications
Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields,
including pattern recognition, robotics, recommendation systems, and gaming. Similarly …
including pattern recognition, robotics, recommendation systems, and gaming. Similarly …
Hybrid attention-oriented experience replay for deep reinforcement learning and its application to a multi-robot cooperative hunting problem
L Yu, S Huo, Z Wang, K Li - Neurocomputing, 2023 - Elsevier
Multiple robots complete a cooperative hunting task by obtaining environmental information
and autonomously learning hunting decision-making strategies. However, with the increase …
and autonomously learning hunting decision-making strategies. However, with the increase …
An overview: Attention mechanisms in multi-agent reinforcement learning
K Hu, K Xu, Q Xia, M Li, Z Song, L Song, N Sun - Neurocomputing, 2024 - Elsevier
In recent years, in the field of Multi-Agent Systems (MAS), significant progress has been
made in the research of algorithms that combine Reinforcement Learning (RL) with Attention …
made in the research of algorithms that combine Reinforcement Learning (RL) with Attention …
Energy-Aware Hierarchical Reinforcement Learning Based on the Predictive Energy Consumption Algorithm for Search and Rescue Aerial Robots in Unknown …
M Ramezani, MA Amiri Atashgah - Drones, 2024 - mdpi.com
Aerial robots (drones) offer critical advantages in missions where human participation is
impeded due to hazardous conditions. Among these, search and rescue missions in disaster …
impeded due to hazardous conditions. Among these, search and rescue missions in disaster …
Structural relational inference actor-critic for multi-agent reinforcement learning
Multi-agent reinforcement learning (MARL) is essential for a wide range of high-dimensional
scenarios and complicated tasks with multiple agents. Many attempts have been made for …
scenarios and complicated tasks with multiple agents. Many attempts have been made for …
From Nash Q-learning to nash-MADDPG: Advancements in multiagent control for multiproduct flexible manufacturing systems
The emergence of flexible manufacturing systems (FMS) capable of processing multiple
product types is a result of the growing demand for product customization and …
product types is a result of the growing demand for product customization and …
Attention-Augmented MADDPG in NOMA-Based Vehicular Mobile Edge Computational Offloading
L Wu, J Qu, S Li, C Zhang, J Du… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
Vehicular mobile edge computing (vMEC) and non-orthogonal multiple access (NOMA)
have emerged as promising technologies for enabling low-latency and high-throughput …
have emerged as promising technologies for enabling low-latency and high-throughput …
强化学习中的注意力机制研究综述.
夏庆锋， 许可儿， 李明阳， 胡凯… - Journal of Frontiers …, 2024 - search.ebscohost.com
近年来, 强化学习与注意力机制的结合在算法研究领域备受瞩目. 在强化学习算法中,
注意力机制的应用在提高算法性能方面发挥了重要作用. 重点聚焦于注意力机制在深度强化学习 …
注意力机制的应用在提高算法性能方面发挥了重要作用. 重点聚焦于注意力机制在深度强化学习 …
Comparing Approaches to Distributed Control of Fluid Systems based on Multi-Agent Systems
KT Logan, JM Stürmer, TM Müller, PF Pelz - arXiv preprint arXiv …, 2022 - arxiv.org
Conventional control of fluid systems does not consider system-wide knowledge for
optimising energy efficient operation. Distributed control of fluid systems combines reliable …
optimising energy efficient operation. Distributed control of fluid systems combines reliable …
Deep Transformers Thirst for Comprehensive-Frequency Data
R Xia, C Xue, B Deng, F Wang, J Wang - arXiv preprint arXiv:2203.07116, 2022 - arxiv.org
Current researches indicate that inductive bias (IB) can improve Vision Transformer (ViT)
performance. However, they introduce a pyramid structure concurrently to counteract the …
performance. However, they introduce a pyramid structure concurrently to counteract the …