Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate
Abstract
Generative adversarial imitation learning (GAIL) demonstrates tremendous success in practice, especially when combined with neural networks. Different from reinforcement learning, GAIL learns both policy and reward function from expert (human) demonstration. Despite its empirical success, it remains unclear whether GAIL with neural networks converges to the globally optimal solution. The major difficulty comes from the nonconvex-nonconcave minimax optimization structure. To bridge the gap between practice and theory, we analyze a gradient-based algorithm with alternating updates and establish its sublinear convergence to the globally optimal solution. To the best of our knowledge, our analysis establishes the global optimality and convergence rate of GAIL with neural networks for the first time.
Cite
@article{arxiv.2003.03709,
title = {Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate},
author = {Yufeng Zhang and Qi Cai and Zhuoran Yang and Zhaoran Wang},
journal= {arXiv preprint arXiv:2003.03709},
year = {2020}
}
Comments
42 pages; accepted to ICML; initial draft submitted in Feb, 2020