Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman Constraints
Tian Xu, Chenyang Wang, Xiaochen Zhai, and 3 more authors
International Conference on Machine Learning, 2026
We explore the role of Bellman constraints in non-adversarial imitation learning to theoretically eliminate compounding errors in long-horizon planning tasks.
