When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence

by   Ziwei Guan, et al.

Generative adversarial imitation learning (GAIL) is a popular inverse reinforcement learning approach for jointly optimizing policy and reward from expert trajectories. A primary question about GAIL is whether applying a certain policy gradient algorithm to GAIL attains a global minimizer (i.e., yields the expert policy), for which existing understanding is very limited. Such global convergence has been shown only for the linear (or linear-type) MDP and linear (or linearizable) reward. In this paper, we study GAIL under general MDP and for nonlinear reward function classes (as long as the objective function is strongly concave with respect to the reward parameter). We characterize the global convergence with a sublinear rate for a broad range of commonly used policy gradient algorithms, all of which are implemented in an alternating manner with stochastic gradient ascent for reward update, including projected policy gradient (PPG)-GAIL, Frank-Wolfe policy gradient (FWPG)-GAIL, trust region policy optimization (TRPO)-GAIL and natural policy gradient (NPG)-GAIL. This is the first systematic theoretical study of GAIL for global convergence.



There are no comments yet.


page 1

page 2

page 3

page 4


On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator

We study the global convergence of generative adversarial imitation lear...

Generative Adversarial Self-Imitation Learning

This paper explores a simple regularizer for reinforcement learning by p...

Policy Gradient Bayesian Robust Optimization for Imitation Learning

The difficulty in specifying rewards for many real-world problems has le...

Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation

In generative adversarial imitation learning (GAIL), the agent aims to l...

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

Generative adversarial imitation learning (GAIL) demonstrates tremendous...

Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies

Policy gradient (PG) methods are a widely used reinforcement learning me...

Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning

We present Imitation-Projected Policy Gradient (IPPG), an algorithmic fr...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.