Distributed Multi-agent Deep Reinforcement Learning For Robust Coordination Against Noise

Abstract

In multi-agent systems, noise reduction techniques are important for improving the overall system reliability as agents are required to rely on limited environmental information to develop cooperative and coordinated behaviors with the surrounding agents. However, previous studies have often applied centralized noise reduction methods to build robust and versatile coordination in noisy multi-agent environments, while distributed and decentralized autonomous agents are more plausible for real-world application. In this paper, we introduce a *distributed attentional actor architecture model for a multi-agent system* (DA3-X), using which we demonstrate that agents with DA3-X can selectively learn the noisy environment and behave cooperatively. We experimentally evaluate the effectiveness of DA3-X by comparing learning methods with and without DA3-X and show that agents with DA3-X can achieve better performance than baseline agents. Furthermore, we visualize heatmaps of *attentional weight

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keymotokawa2022distributed

Related papers

• Interpretability For Conditional Coordinated Behavior In Multi-agent Reinforcement Learning (2023)3.58
• Multi-agent Deep Reinforcement Learning With Extremely Noisy Observations (2018)0.00
• Noise Distribution Decomposition Based Multi-agent Distributional Reinforcement Learning (2023)0.00
• DSDF: An Approach To Handle Stochastic Agents In Collaborative Multi-agent Reinforcement Learning (2021)0.00
• Hierarchical Reinforcement Learning With Opponent Modeling For Distributed Multi-agent Cooperation (2022)5.84
• Research On Multi-agent Communication And Collaborative Decision-making Based On Deep Reinforcement Learning (2023)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Optimization For Reinforcement Learning: From Single Agent To Cooperative Agents (2019)14.62