Soft Hierarchical Graph Recurrent Networks For Many-agent Partially Observable Environments

Abstract

The recent progress in multi-agent deep reinforcement learning(MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and the partially observable constraints raise challenges to its performance and deployment. Based on our intuitive observation that the human society could be regarded as a large-scale partially observable environment, where each individual has the function of communicating with neighbors and remembering its own experience, we propose a novel network structure called hierarchical graph recurrent network(HGRN) for multi-agent cooperation under partial observability. Specifically, we construct the multi-agent system as a graph, use the hierarchical graph attention network(HGAT) to achieve communication between neighboring agents, and exploit GRU to enable agents to record historical information. To encourage exploration and improve robustness, we design a maximum-entropy learning method to learn stochastic policies of a configurable targe

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyye2021soft

Related papers

• Subgoal-based Hierarchical Reinforcement Learning For Multi-agent Collaboration (2024)0.00
• Efficient Policy Generation In Multi-agent Systems Via Hypergraph Neural Network (2022)0.00
• Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations (2020)0.00
• Self-clustering Hierarchical Multi-agent Reinforcement Learning With Extensible Cooperation Graph (2024)2.26
• Multi-agent Deep Reinforcement Learning With Extremely Noisy Observations (2018)0.00
• Towards Heterogeneous Multi-agent Reinforcement Learning With Graph Neural Networks (2020)6.34
• Hierarchical Reinforcement Learning In Complex 3D Environments (2023)0.00
• Hierarchical Reinforcement Learning With Opponent Modeling For Distributed Multi-agent Cooperation (2022)5.84