Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations

Abstract

Multi-agent reinforcement learning (MARL) has been increasingly explored to learn the cooperative policy towards maximizing a certain global reward. Many existing studies take advantage of graph neural networks (GNN) in MARL to propagate critical collaborative information over the interaction graph, built upon inter-connected agents. Nevertheless, the vanilla GNN approach yields substantial defects in dealing with complex real-world scenarios since the generic message passing mechanism is ineffective between heterogeneous vertices and, moreover, simple message aggregation functions are incapable of accurately modeling the combinational interactions from multiple neighbors. While adopting complex GNN models with more informative message passing and aggregation mechanisms can obviously benefit heterogeneous vertex representations and cooperative policy learning, it could, on the other hand, increase the training difficulty of MARL and demand more intense and direct reward signals compare

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshi2020cooperative

Related papers

• Enhancing Heterogeneous Multi-agent Cooperation In Decentralized MARL Via Gnn-driven Intrinsic Rewards (2024)0.00
• Heterogeneous Multi-robot Reinforcement Learning (2023)6.77
• Efficient Policy Generation In Multi-agent Systems Via Hypergraph Neural Network (2022)0.00
• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00
• Towards Heterogeneous Multi-agent Reinforcement Learning With Graph Neural Networks (2020)6.34
• A Survey Of Multi-agent Deep Reinforcement Learning With Graph Neural Network-based Communication (2026)0.00
• Self-clustering Hierarchical Multi-agent Reinforcement Learning With Extensible Cooperation Graph (2024)2.26
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34