Revisiting The Master-slave Architecture In Multi-agent Deep Reinforcement Learning

Abstract

Many tasks in artificial intelligence require the collaboration of multiple agents. We exam deep reinforcement learning for multi-agent domains. Recent research efforts often take the form of two seemingly conflicting perspectives, the decentralized perspective, where each agent is supposed to have its own controller; and the centralized perspective, where one assumes there is a larger model controlling all agents. In this regard, we revisit the idea of the master-slave architecture by incorporating both perspectives within one framework. Such a hierarchical structure naturally leverages advantages from one another. The idea of combining both perspectives is intuitive and can be well motivated from many real world systems, however, out of a variety of possible realizations, we highlights three key ingredients, i.e. composed action representation, learnable communication and independent reasoning. With network designs to facilitate these explicitly, our proposal consistently outperforms

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykong2017revisiting

Related papers

• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• A Review Of Cooperative Multi-agent Deep Reinforcement Learning (2019)19.08
• Deep Reinforcement Learning For Multi-agent Interaction (2022)9.23
• Decentralized Multi-agent Reinforcement Learning With Networked Agents: Recent Advances (2019)0.00
• Deep Reinforcement Learning For Multi-agent Systems: A Review Of Challenges, Solutions And Applications (2018)22.57
• Multi-agent Reinforcement Learning: A Report On Challenges And Approaches (2018)0.00
• Exploring Task-oriented Communication In Multi-agent System: A Deep Reinforcement Learning Approach (2022)0.00
• From Centralized To Self-supervised: Pursuing Realistic Multi-agent Reinforcement Learning (2023)0.00