Adaptive Value Decomposition With Greedy Marginal Contribution Computation For Cooperative Multi-agent Reinforcement Learning

Abstract

Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods are among those cutting-edge solutions. However, traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. This hinders their application in generic scenarios. Recent methods tackle this problem from the perspective of implicit credit assignment by learning value functions with complete expressiveness or using additional structures to improve cooperation. However, they are either difficult to learn due to large joint action spaces or insufficient to capture the complicated interactions among agents which are essential to solving tasks with non-monotonic returns. To address these problems, we propose a novel explicit credit assignment method to address the non-mono

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyliu2023adaptive

Related papers

• Understanding Value Decomposition Algorithms In Deep Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Dual Self-awareness Value Decomposition Framework Without Individual Global Max For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Boosting Value Decomposition Via Unit-wise Attentive State Representation For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Locality Matters: A Scalable Value Decomposition Approach For Cooperative Multi-agent Reinforcement Learning (2021)0.00
• SVDE: Scalable Value-decomposition Exploration For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Revisiting Some Common Practices In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Decom: Decomposed Policy For Constrained Cooperative Multi-agent Reinforcement Learning (2021)0.00