A differential dynamic programming framework for inverse reinforcement learning

• المؤلفون الرئيسيون: Cao, Kun, Xu, Xinhang, Jin, Wanxin, Johansson, Karl H., Xie, Lihua
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2025
• الموضوعات: Engineering; Inverse reinforcement learning; Constrained optimal control
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/181965; http://arxiv.org/abs/2407.19902v1
• المؤسسة: Nanyang Technological University

A differential dynamic programming (DDP)-based framework for inverse reinforcement learning (IRL) is introduced to recover the parameters in the cost function, system dynamics, and constraints from demonstrations. Different from existing work, where DDP was used for the inner forward problem with...