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

Jul 12, 2020



Generative adversarial imitation learning (GAIL) demonstrates tremendous success in practice, especially when combined with neural network parameterization. Different from reinforcement learning, GAIL learns the policy and reward function from the expert (human) demonstration. Despite its empirical success, it remains unclear whether GAIL with neural network parameterization converges to the globally optimal solution. The major difficulty comes from the underlying nonconvex-nonconcave structure. To bridge the gap between theory and practice, we analyze the gradient-based alternating update algorithm and establish its sublinear convergence to the globally optimal solution. To the best of our knowledge, our analysis establishes the first global optimality and convergence guarantees for GAIL with neural network parameterization.



About ICML 2020

The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

Store presentation

Should this presentation be stored for 1000 years?

How do we store presentations

Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%


Recommended Videos

Presentations on similar topic, category or speaker

Interested in talks like this? Follow ICML 2020