Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
Not on the map. Why?
Abstract (arXiv)
Recent years have witnessed the great success of multi-agent systems (MAS). Value decomposition, which decomposes joint action values into individual action values, has been an important work in MAS. However, many value decomposition methods ignore the coordination among different agents, leading to the notorious "lazy agents" problem. To enhance the coordination in MAS, this paper proposes HyperGraph CoNvolution MIX (HGCN-MIX), a method that incorporates hypergraph convolution with value decomposition. HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards. Then, it trains a hypergraph that can capture the collaborative relationships among agents. Leveraging the learned hypergraph to consider how other agents' observations and actions affect their decisions, the agents in a MAS can better coordinate. We evaluate HGCN-MIX in the StarCraft II multi-agent challenge benchmark. The experimental results demonstrate that HGCN-MIX can train joint policies that outperform or achieve a similar level of performance as the current state-of-the-art techniques. We also observe that HGCN-MIX has an even more significant improvement of performance in the scenarios with a large amount of agents. Besides, we conduct additional analysis to emphasize that when the hypergraph learns more relationships, HGCN-MIX can train stronger joint policies.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 9 Dec 2021.
Builds on
27 of 41 references.
References · 27
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
- 2015End-to-End Training of Deep Visuomotor Policiescited by 875
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
- 2019The StarCraft Multi-Agent Challengecited by 597
- 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
- 2018Hypergraph Neural Networkscited by 488
- 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
15 more
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
- 2019Hypergraph Convolution and Hypergraph Attentioncited by 228
- 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
- 2018Mean Field Multi-Agent Reinforcement Learningcited by 207
- 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 184
- 2018Graph Convolutional Reinforcement Learningcited by 152
- 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
- 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
- 2019Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learningcited by 93
- 2018Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networkscited by 56
- 2020Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learningcited by 14
- 2020Distributional Reinforcement Learning via Moment Matchingcited by 10
- 2021MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learningcited by 6
- 2019UW-MARL: Multi-Agent Reinforcement Learning for Underwater Adaptive Sampling using Autonomous Vehiclescited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 2.
3 papers.