基于模型预测的对抗模仿学习用于从观察中规划
Model Predictive Adversarial Imitation Learning for Planning from Observation
AI总结：
本文提出一种基于模型预测的对抗模仿学习方法，通过端到端学习从观察中规划，提升样本效率和鲁棒性。
摘要：
人类示范数据通常模糊且不完整，推动了能够表现出可靠规划行为的模仿学习方法。一种常见的从示范中规划的方法涉及通过逆强化学习（IRL）学习奖励函数，然后通过模型预测控制（MPC）部署该奖励。为了统一这些方法，我们推导出将IRL中的策略替换为基于规划的智能体。借助对抗模仿学习的联系，这种形式使从仅观察到的示范中端到端地学习规划器成为可能。除了在可解释性、复杂性和安全性方面的优势外，我们还研究并观察到在样本效率、分布外泛化和鲁棒性方面有显著改进。本研究包括在模拟控制基准和使用少量到单个观察到的示范的现实世界导航实验中的评估。
英文摘要：
Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function via Inverse Reinforcement Learning (IRL) then deploying this reward via Model Predictive Control (MPC). Towards unifying these methods, we derive a replacement of the policy in IRL with a planning-based agent. With connections to Adversarial Imitation Learning, this formulation enables end-to-end interactive learning of planners from observation-only demonstrations. In addition to benefits in interpretability, complexity, and safety, we study and observe significant improvements on sample efficiency, out-of-distribution generalization, and robustness. The study includes evaluations in both simulated control benchmarks and real-world navigation experiments using few-to-single observation-only demonstrations.
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。
