让智能体在通信受损时仍能高效协作，提升多智能体系统鲁棒性。
Multi-Agent Reinforcement Learning with Communication-Constrained Priors
- 用统一模型刻画不同通信条件，作为学习先验区分消息损毁与否
- 解耦损毁与完好消息对决策的影响，量化通信价值至全局奖励
- 适用于通信不稳定的真实复杂场景，尤其适合工业级多智能体系统
通信是提升多智能体系统协同策略学习的有效手段。然而，在多数真实场景中，通信损耗普遍存在。现有带通信的多智能体强化学习方法因可扩展性与鲁棒性不足，难以应用于复杂动态环境。为此，我们提出一种广义的通信受限模型，统一表征不同场景下的通信条件，并将其作为学习先验，以区分特定场景中损毁与无损消息。此外，我们基于双互信息估计器，解耦损毁与无损消息对分布式决策的影响，引入一种通信受限的多智能体强化学习框架，将通信消息的影响量化至全局奖励。最后，我们在多个通信受限基准上验证了该方法的有效性。
原文摘要 · Abstract (English)
Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。