Multi-task Multi-agent Shared Layers Are Universal Cognition Of Multi-agent Coordination

Abstract

Multi-agent reinforcement learning shines as the pinnacle of multi-agent systems, conquering intricate real-world challenges, fostering collaboration and coordination among agents, and unleashing the potential for intelligent decision-making across domains. However, training a multi-agent reinforcement learning network is a formidable endeavor, demanding substantial computational resources to interact with diverse environmental variables, extract state representations, and acquire decision-making knowledge. The recent breakthroughs in large-scale pre-trained models ignite our curiosity: Can we uncover shared knowledge in multi-agent reinforcement learning and leverage pre-trained models to expedite training for future tasks? Addressing this issue, we present an innovative multi-task learning approach that aims to extract and harness common decision-making knowledge, like cooperation and competition, across different tasks. Our approach involves concurrent training of multiple multi-age

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2023multi

Related papers

• Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00
• Collaboration Of AI Agents Via Cooperative Multi-agent Deep Reinforcement Learning (2019)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Revisiting The Master-slave Architecture In Multi-agent Deep Reinforcement Learning (2017)0.00
• Modeling Sensorimotor Coordination As Multi-agent Reinforcement Learning With Differentiable Communication (2019)0.00
• Learning In Cooperative Multiagent Systems Using Cognitive And Machine Models (2023)7.81
• Deep Decentralized Multi-task Multi-agent Reinforcement Learning Under Partial Observability (2017)0.00
• ALMA: Hierarchical Learning For Composite Multi-agent Tasks (2022)0.00