From Centralized To Self-supervised: Pursuing Realistic Multi-agent Reinforcement Learning

Abstract

In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent Reinforcement Learning (MARL) methods adopt centralized approaches that involve either centralized training or reward-sharing, often violating the realistic ways in which living organisms, like animals or humans, process information and interact. MARL strategies deploying decentralized training with intrinsic motivation offer a self-supervised approach, enable agents to develop flexible social strategies through the interaction of autonomous agents. However, by contrasting the self-supervised and centralized methods, we reveal that populations trained with reward-sharing methods surpass those using self-supervised methods in a mixed-motive environment. We link this superiority to specialized role emergence and an agent's expertise in its role. Interesting

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxiang2023from

Related papers

• Decentralized Multi-agent Reinforcement Learning With Networked Agents: Recent Advances (2019)0.00
• Mean-field Multi-agent Reinforcement Learning: A Decentralized Network Approach (2021)0.00
• Fully Decentralized Cooperative Multi-agent Reinforcement Learning: A Survey (2024)0.00
• An Initial Introduction To Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Contextual Knowledge Sharing In Multi-agent Reinforcement Learning With Decentralized Communication And Coordination (2025)0.00
• Decentralized Multi-agents By Imitation Of A Centralized Controller (2019)0.00
• Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84
• Robust Multi-agent Reinforcement Learning With Social Empowerment For Coordination And Communication (2020)0.00