Multi-agent reinforcement learning: A review of challenges and applications

L Canese, GC Cardarilli, L Di Nunzio, R Fazzolari… - Applied Sciences, 2021 - mdpi.com
In this review, we present an analysis of the most used multi-agent reinforcement learning
algorithms. Starting with the single-agent reinforcement learning algorithms, we focus on the …

[HTML][HTML] A survey on multi-agent reinforcement learning and its application

Z Ning, L **e - Journal of Automation and Intelligence, 2024 - Elsevier
Multi-agent reinforcement learning (MARL) has been a rapidly evolving field. This paper
presents a comprehensive survey of MARL and its applications. We trace the historical …

Resilient multi-agent RL: introducing DQ-RTS for distributed environments with data loss

L Canese, GC Cardarilli, L Di Nunzio, R Fazzolari… - Scientific Reports, 2024 - nature.com
This paper proposes DQ-RTS, a novel decentralized Multi-Agent Reinforcement Learning
algorithm designed to address challenges posed by non-ideal communication and a varying …

Radar-jamming decision-making based on improved Q-learning and FPGA hardware implementation

S Zheng, C Zhang, J Hu, S Xu - Remote Sensing, 2024 - mdpi.com
In contemporary warfare, radar countermeasures have become multifunctional and
intelligent, rendering the conventional jamming method and platform unsuitable for the …

Accelerating multi-agent ddpg on cpu-fpga heterogeneous platform

S Wiggins, Y Meng, R Kannan… - 2023 IEEE High …, 2023 - ieeexplore.ieee.org
Multi-Agent Reinforcement Learning (MARL) is a key technology in artificial intelligence
applications such as robotics, surveillance, energy systems, etc. Multi-Agent Deep …

“MR Q-Learning” Algorithm for Efficient Hardware Implementations

GC Cardarilli, L Di Nunzio, R Fazzolari… - 2021 55th Asilomar …, 2021 - ieeexplore.ieee.org
The maximum value finder block is one of the most critical parts in the hardware
implementation of the Q-Learning Reinforcement Learning algorithm. To solve this issue, we …

[PDF][PDF] Journal of Automation and Intelligence

Z Ning, L **e - researchgate.net
Multi-agent reinforcement learning (MARL) has been a rapidly evolving field. This paper
presents a comprehensive survey of MARL and its applications. We trace the historical …