Maca: a multi-agent reinforcement learning platform for collective intelligence

F Gao, S Chen, M Li, B Huang - 2019 IEEE 10th International …, 2019 - ieeexplore.ieee.org
Heterogeneous multi-agent cooperative decisionmaking is one of the kernel problems in
collective intelligence field. Reinforcement learning may be an effective technology to …

Decentralized multi-agent reinforcement learning with shared actions

RK Mishra, D Vasal… - 2021 55th Annual …, 2021 - ieeexplore.ieee.org
In this paper, we consider a multi-agent system with N cooperative agents where each agent
privately observes its own private type and publicly observes each others' actions. We …

Aggregation transfer learning for multi-agent reinforcement learning

D Xu, P Qiao, Y Dou - … International Conference on Big Data & …, 2021 - ieeexplore.ieee.org
Multi-agent reinforcement learning is currently mainly used in many real-time strategy
games. For example, StarCraft, UAV combat. Multi-agent reinforcement learning algorithms …

Survey of multi-agent strategy based on reinforcement learning

L Chen, T Guo, Y Liu, J Yang - 2020 Chinese Control And …, 2020 - ieeexplore.ieee.org
There are many multi-agent systems in life, such as driving vehicles, playing football games,
and even bees building their hives. These systems are cooperative or competitive among …

Stateful active facilitator: Coordination and environmental heterogeneity in cooperative multi-agent reinforcement learning

D Liu, V Shah, O Boussif, C Meo, A Goyal… - arXiv preprint arXiv …, 2022 - arxiv.org
In cooperative multi-agent reinforcement learning, a team of agents works together to
achieve a common goal. Different environments or tasks may require varying degrees of …

MaDE: Multi-Scale Decision Enhancement for Multi-Agent Reinforcement Learning

J Ruan, R Xie, X Xiong, S Xu… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
In the domain of multi-agent reinforcement learning (MARL), the limited information
availability, complex agent interactions, and individual capabilities among agents often pose …

A contrastive-enhanced ensemble framework for efficient multi-agent reinforcement learning

X Du, H Chen, Y Xing, SY Philip, L He - Expert Systems with Applications, 2024 - Elsevier
Multi-agent reinforcement learning is promising for real-world applications as it encourages
agents to perceive and interact with their surrounding environment autonomously. However …

RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning

W Qiu, X Ma, B An, S Obraztsova… - The Eleventh …, 2023 - openreview.net
Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL
agents easily overfit the training environment and perform poorly in evaluation scenarios …

A review of cooperative multi-agent deep reinforcement learning

A Oroojlooy, D Hajinezhad - Applied Intelligence, 2023 - Springer
Abstract Deep Reinforcement Learning has made significant progress in multi-agent
systems in recent years. The aim of this review article is to provide an overview of recent …

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning

K Zhang, DD Zhu, Q Xu, H Zhou, C Zheng - arXiv preprint arXiv …, 2024 - arxiv.org
Training for multi-agent reinforcement learning (MARL) is a time-consuming process caused
by distribution shift of each agent. One drawback is that strategy of each agent in MARL is …