TERL：基于Transformer增强强化学习的大规模多目标合围
TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement Learning
AI总结：
本文提出TERL框架，通过Transformer策略网络与目标选择机制实现大规模多目标合围，并在小规模训练后零样本泛化至80追捕者、20目标场景，取得100%成功率。
摘要：
追逃（PE）问题是多机器人系统（MRS）中的一项关键挑战。尽管强化学习（RL）在解决追逃任务中已展现出潜力，但研究主要集中在单目标追捕上，对多目标合围的探索有限，尤其是在大规模场景下。本文提出了一种用于大规模多目标合围的Transformer增强强化学习（TERL）框架。通过将基于Transformer的策略网络与目标选择相结合，TERL使机器人能够自适应地确定目标优先级并安全地协调机器人。结果表明，TERL在合围成功率和任务完成时间方面优于现有的基于RL的方法，同时在大规模场景中保持良好的性能。值得注意的是，TERL在小规模场景（15个追捕者、4个目标）上训练后，无需重新训练即可有效泛化到大规模场景（80个追捕者、20个目标），实现了100%的成功率。代码和演示视频可在https://github.com/ApricityZ/TERL获取。
英文摘要：
Pursuit-evasion (PE) problem is a critical challenge in multi-robot systems (MRS). While reinforcement learning (RL) has shown its promise in addressing PE tasks, research has primarily focused on single-target pursuit, with limited exploration of multi-target encirclement, particularly in large-scale settings. This paper proposes a Transformer-Enhanced Reinforcement Learning (TERL) framework for large-scale multi-target encirclement. By integrating a transformer-based policy network with target selection, TERL enables robots to adaptively prioritize targets and safely coordinate robots. Results show that TERL outperforms existing RL-based methods in terms of encirclement success rate and task completion time, while maintaining good performance in large-scale scenarios. Notably, TERL, trained on small-scale scenarios (15 pursuers, 4 targets), generalizes effectively to large-scale settings (80 pursuers, 20 targets) without retraining, achieving a 100% success rate. The code and demonstration video are available at https://github.com/ApricityZ/TERL.
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。
