Skip to yearly menu bar Skip to main content


Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate

Yufeng Zhang · Qi Cai · Zhuoran Yang · Zhaoran Wang

Keywords: [ Planning and Control ] [ Planning, Control, and Multiagent Learning ]


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.

Chat is not available.