通过信任机制让智能体互教，加速通信协议演化
Trust-Based Social Learning for Communication (TSLEC) Protocol Evolution in Multi-Agent Reinforcement Learning
- 智能体基于信任关系选择性传授成功策略
- 收敛速度提升23.9%，协议更适应动态目标
- 适合研究多智能体协作与自组织通信的学者
多智能体系统中的涌现通信通常依赖独立学习，导致收敛慢且协议可能次优。我们提出TSLEC（基于信任的社会学习与涌现通信），让智能体显式地向同伴传授成功策略，并由学习到的信任关系调控知识传递。在30个随机种子、共100轮实验中，相比独立学习，信任驱动的社会学习使收敛所需轮数减少23.9%（p < 0.001，Cohen's d = 1.98），生成的协议具有0.38的组合性（C = 0.38），在动态目标下仍保持高鲁棒性（解码准确率Phi > 0.867）。信任评分与教学质量高度相关（r = 0.743，p < 0.001），实现有效知识筛选。结果表明，显式社会学习能根本性加速多智能体协调中的涌现通信。
原文摘要 · Abstract (English)
Emergent communication in multi-agent systems typically occurs through independent learning, resulting in slow convergence and potentially suboptimal protocols. We introduce TSLEC (Trust-Based Social Learning with Emergent Communication), a framework where agents explicitly teach successful strategies to peers, with knowledge transfer modulated by learned trust relationships. Through experiments with 100 episodes across 30 random seeds, we demonstrate that trust-based social learning reduces episodes-to-convergence by 23.9% (p < 0.001, Cohen's d = 1.98) compared to independent emergence, while producing compositional protocols (C = 0.38) that remain robust under dynamic objectives (Phi > 0.867 decoding accuracy). Trust scores strongly correlate with teaching quality (r = 0.743, p < 0.001), enabling effective knowledge filtering. Our results establish that explicit social learning fundamentally accelerates emergent communication in multi-agent coordination.
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。