Measuring Collaborative Emergent Behavior In Multi-agent Reinforcement Learning

Abstract

Multi-agent reinforcement learning (RL) has important implications for the future of human-agent teaming. We show that improved performance with multi-agent RL is not a guarantee of the collaborative behavior thought to be important for solving multi-agent tasks. To address this, we present a novel approach for quantitatively assessing collaboration in continuous spatial tasks with multi-agent RL. Such a metric is useful for measuring collaboration between computational agents and may serve as a training signal for collaboration in future RL paradigms involving humans.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keybarton2018measuring

Related papers

• Collaboration Promotes Group Resilience In Multi-agent RL (2021)0.00
• Emergent Social Learning Via Multi-agent Reinforcement Learning (2020)0.00
• The Impact Of Behavioral Diversity In Multi-agent Reinforcement Learning (2024)0.00
• Multi-agent Reinforcement Learning: A Report On Challenges And Approaches (2018)0.00
• Collaboration Of AI Agents Via Cooperative Multi-agent Deep Reinforcement Learning (2019)0.00
• Cooperative Informative Sensing For Monitoring Dynamic Indoor Environments Via Multi-agent Reinforcement Learning (2026)0.00
• Stigmergic Independent Reinforcement Learning For Multi-agent Collaboration (2019)10.85
• PMIC: Improving Multi-agent Reinforcement Learning With Progressive Mutual Information Collaboration (2022)0.00