Multi-agent Game Abstraction Via Graph Attention Neural Network

Abstract

In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection me

Stats

• citations185
• S2 citations—
• github stars0
• HF likes0
• heat score17.02
• arxiv keyliu2019multi

Related papers

• Efficient Policy Generation In Multi-agent Systems Via Hypergraph Neural Network (2022)0.00
• Multi-agent Deep Reinforcement Learning Using Attentive Graph Neural Architectures For Real-time Strategy Games (2021)7.16
• A Survey Of Multi-agent Deep Reinforcement Learning With Graph Neural Network-based Communication (2026)0.00
• Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations (2020)0.00
• Foresight Of Graph Reinforcement Learning Latent Permutations Learnt By Gumbel Sinkhorn Network (2021)0.00
• Cooperative Multi-agent Reinforcement Learning With Hypergraph Convolution (2021)5.84
• Group-aware Coordination Graph For Multi-agent Reinforcement Learning (2024)0.00
• Soft Hierarchical Graph Recurrent Networks For Many-agent Partially Observable Environments (2021)0.00