基于知识蒸馏的人类启发式多智能体导航
Human-Inspired Multi-Agent Navigation using Knowledge Distillation
AI总结：
本文提出一种结合知识蒸馏与强化学习的框架，利用人类轨迹演示提取专家策略以塑造奖励，训练多智能体在分散环境中学习人类式避碰策略，并在未演示任务中超越专家。
摘要：
尽管多智能体导航领域取得了显著进展，但智能体在多智能体环境中仍缺乏人类所表现出的复杂性和智能。在本文中，我们提出了一种框架，用于在完全分散的多智能体环境中学习针对智能体间交互的人类式通用避碰策略。我们的方法使用知识蒸馏结合强化学习，基于通过行为克隆从人类轨迹演示中提取的专家策略来塑造奖励函数。我们表明，使用我们的方法训练的智能体能够在演示未提供的避碰和目标导向导航任务中采取人类式轨迹，其性能优于专家以及未经知识蒸馏训练的学习型智能体。
英文摘要：
Despite significant advancements in the field of multi-agent navigation, agents still lack the sophistication and intelligence that humans exhibit in multi-agent settings. In this paper, we propose a framework for learning a human-like general collision avoidance policy for agent-agent interactions in fully decentralized, multi-agent environments. Our approach uses knowledge distillation with reinforcement learning to shape the reward function based on expert policies extracted from human trajectory demonstrations through behavior cloning. We show that agents trained with our approach can take human-like trajectories in collision avoidance and goal-directed steering tasks not provided by the demonstrations, outperforming the experts as well as learning-based agents trained without knowledge distillation.
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。
