Impact Of Relational Networks In Multi-agent Learning: A Value-based Factorization View

Abstract

Effective coordination and cooperation among agents are crucial for accomplishing individual or shared objectives in multi-agent systems. In many real-world multi-agent systems, agents possess varying abilities and constraints, making it necessary to prioritize agents based on their specific properties to ensure successful coordination and cooperation within the team. However, most existing cooperative multi-agent algorithms do not take into account these individual differences, and lack an effective mechanism to guide coordination strategies. We propose a novel multi-agent learning approach that incorporates relationship awareness into value-based factorization methods. Given a relational network, our approach utilizes inter-agents relationships to discover new team behaviors by prioritizing certain agents over other, accounting for differences between them in cooperative tasks. We evaluated the effectiveness of our proposed approach by conducting fifteen experiments in two different

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfindik2023impact

Related papers

• Analysing Factorizations Of Action-value Networks For Cooperative Multi-agent Reinforcement Learning (2019)2.26
• Towards Understanding Cooperative Multi-agent Q-learning With Value Factorization (2020)0.00
• Reward-sharing Relational Networks In Multi-agent Reinforcement Learning As A Framework For Emergent Behavior (2022)2.26
• Networked Agents In The Dark: Team Value Learning Under Partial Observability (2025)0.00
• Residual Q-networks For Value Function Factorizing In Multi-agent Reinforcement Learning (2022)10.21
• Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Relational Forward Models For Multi-agent Learning (2018)0.00
• RACA: Relation-aware Credit Assignment For Ad-hoc Cooperation In Multi-agent Deep Reinforcement Learning (2022)3.58