提出双蒸馏网络，提升多智能体协作在信息受限下的稳定性与性能。
Double Distillation Network for Multi-Agent Reinforcement Learning
- 设计内外双蒸馏模块，缓解训练与执行间的观测差异。
- 在多个场景中显著提升多智能体协作效果，克服部分可观测带来的误差累积。
- 适合研究多智能体强化学习协同机制的科研人员参考。
多智能体强化学习通常采用集中训练、分散执行（CTDE）框架以缓解环境非平稳性问题。然而，执行阶段的部分可观测性可能导致智能体累积误差，影响有效协作策略的训练。为此，我们提出双蒸馏网络（DDN），包含两个蒸馏模块，旨在增强鲁棒协作并促进受限信息下的合作过程。外部蒸馏模块通过全局引导网络与局部策略网络，利用蒸馏技术弥合全局训练与局部执行之间的差距。内部蒸馏模块引入基于状态信息的内在奖励，提升智能体的探索能力。大量实验表明，DDN在多个场景中显著提升了性能。
原文摘要 · Abstract (English)
Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulative gap errors gathered by agents, impairing the training of effective collaborative policies. To overcome this challenge, we introduce the Double Distillation Network (DDN), which incorporates two distillation modules aimed at enhancing robust coordination and facilitating the collaboration process under constrained information. The external distillation module uses a global guiding network and a local policy network, employing distillation to reconcile the gap between global training and local execution. In addition, the internal distillation module introduces intrinsic rewards, drawn from state information, to enhance the exploration capabilities of agents. Extensive experiments demonstrate that DDN significantly improves performance across multiple scenarios.
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。