少即是多：通过表征简洁性实现鲁棒的零通信三维追捕-逃避
Less is More: Robust Zero-Communication 3D Pursuit-Evasion via Representational Parsimony
AI总结：
通过表征简洁性提升零通信下的三维追捕-逃避鲁棒性，采用简洁的智能体观察接口和贡献门控信用分配方法，实现更高的成功率和更少的碰撞。
摘要：
在杂乱的体素环境中，不对称的三维追捕-逃避在通信延迟、部分可观测性和非完整运动限制下具有挑战性。尽管许多多智能体强化学习方法依赖于更丰富的智能体间耦合或集中信号，但这些依赖性在通信延迟或嘈杂时可能成为脆弱源。基于继承的路径引导去中心化追捕框架，我们研究了一个以鲁棒性为导向的问题：表征简洁性能否提高无通信协调？我们通过（i）一个简洁的智能体观察接口来实例化这一原则，该接口移除了团队耦合通道（从83维到50维），以及（ii）贡献门控信用分配（CGCA），一种局部意识的信用结构，用于无通信合作。在第五阶段评估（4个追捕者对1个逃避者）中，我们的配置达到了0.753±0.091的成功率和0.223±0.066的碰撞率，优于83维FULL OBS对照组（0.721±0.071，0.253±0.089）。它进一步在速度/偏转/噪声/延迟压力测试中表现出优雅的退化，并在城市峡谷地图上显示了对无监督迁移的韧性（在密度0.24时大约61%的成功率）。这些结果支持了一种实用的范式转变：显式切断冗余的跨智能体通道可以抑制累积误差级联并提高在延迟多发部署中的鲁棒性。
英文摘要：
Asymmetric 3D pursuit-evasion in cluttered voxel environments is difficult under communication latency, partial observability, and nonholonomic maneuver limits. While many MARL methods rely on richer inter-agent coupling or centralized signals, these dependencies can become fragility sources when communication is delayed or noisy. Building on an inherited path-guided decentralized pursuit scaffold, we study a robustness-oriented question: can representational parsimony improve communication-free coordination? We instantiate this principle with (i) a parsimonious actor observation interface that removes team-coupled channels (83-D to 50-D), and (ii) Contribution-Gated Credit Assignment (CGCA), a locality-aware credit structure for communication-denied cooperation. In Stage-5 evaluation (4 pursuers vs. 1 evader), our configuration reaches 0.753 +/- 0.091 success and 0.223 +/- 0.066 collision, outperforming the 83-D FULL OBS counterpart (0.721 +/- 0.071, 0.253 +/- 0.089). It further shows graceful degradation under speed/yaw/noise/delay stress tests and resilient zero-shot transfer on urban-canyon maps (about 61% success at density 0.24). These results support a practical paradigm shift: explicitly severing redundant cross-agent channels can suppress compounding error cascades and improve robustness in latency-prone deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
