通信正則化を備えた安全な異種マルチエージェント強化学習による協調的目標獲得
Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition
異種エージェントチームが部分観測・通信制約下で目標を協調探索・獲得するため、グラフ注意ネットワークと安全フィルタを統合した分散型MARLフレームワークを提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Gabriele Calzolari, Vidya Sumathy, Christoforos Kanellakis, George Nikolakopoulos
分類: cs.RO, cs.AI
原文アブストラクト
This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterized by partial observability, communication constraints, and dynamic interactions. Each agent's policy is trained with the Multi-Agent Proximal Policy Optimization algorithm and employs a Graph Attention Network encoder that integrates simulated range-sensing data with communication embeddings exchanged among neighboring agents, enabling context-aware decision-making from both local sensing and relational information. In particular, this work introduces a unified framework that integrates graph-based communication and trajectory-aware safety through safety filters. The architecture is supported by a structured reward formulation designed to encourage effective target discovery and acquisition, collision avoidance, and de-correlation between the agents' communication vectors by promoting informational orthogonality. The effectiveness of the proposed reward function is demonstrated through a comprehensive ablation study. Moreover, simulation results demonstrate safe and stable task execution, confirming the framework's effectiveness.
