发表机构
Nanjing University; Hong Kong Polytechnic University; Shenzhen University（南京大学; 香港理工大学; 深圳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ELV框架，通过潜在概念与双路径注意力机制使多智能体决策透明化，并利用概念预测内在奖励促进探索，在多个环境中兼顾性能与可解释性。
AI 中文摘要
在多智能体强化学习中，由于每个智能体通常只能部分观测环境，高效协作颇具挑战性。循环网络编码局部交互历史，但其隐藏表示对个体决策背后的信息提供的洞察有限。为应对这些挑战，我们提出一种新颖的可解释框架，称为逃离局部视角（ELV），该框架引入语义结构化的潜在概念，使策略决策透明化。具体而言，每个智能体从其局部观测和动作-观测轨迹中提取低维语义概念。这些概念通过变分自编码器（VAE）联合编码为上下文潜在变量，从而在局部视角与全局语义之间建立桥梁。为显式建模每个智能体的决策，我们采用双路径注意力机制，其中一个模块估计各概念相对于全局上下文的显著性，另一个模块通过成对概念交互捕捉高阶协作模式。此外，我们引入概念预测模块，该模块根据下一概念预测误差推导内在奖励，激励智能体探索语义新颖区域。在多个环境中的实验验证表明，ELV不仅实现了有竞争力的性能，还显式提供了智能体如何推理其决策的机制。
英文摘要
Efficient cooperation is challenging due to the usual partial observability of each agent in multi-agent reinforcement learning. Recurrent networks encode local interaction histories, but their hidden representations provide limited insight into the information underlying individual decisions. To address these challenges, we propose a novel interpretable framework, called escaping local views (ELV), which introduces semantically structured latent concepts to render policy decisions transparent. Specifically, each agent extracts low-dimensional semantic concepts from its local observation and action-observation trajectory. These concepts are jointly encoded into a contextual latent variable via a variational autoencoder (VAE), which builds a bridge between local views and global semantics. To explicitly model the decision of each agent, we employ a dual-path attention mechanism in which one module estimates the salience of individual concepts relative to the global context, while the other captures higher-order cooperative patterns with pairwise concept interactions. Furthermore, we incorporate a concept prediction module that derives an intrinsic reward from next-concept prediction errors, which incentivizes agents to explore regions of semantic novelty. Experiments in multiple environments verify that ELV not only achieves competitive performance but also explicitly provides how agents reason about their decisions.
