When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence

06/24/2020
by   Ziwei Guan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/11/2019

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

We study the global convergence of generative adversarial imitation lear...
12/03/2018

Generative Adversarial Self-Imitation Learning

This paper explores a simple regularizer for reinforcement learning by p...
06/11/2021

Policy Gradient Bayesian Robust Optimization for Imitation Learning

The difficulty in specifying rewards for many real-world problems has le...
03/08/2020

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

Generative adversarial imitation learning (GAIL) demonstrates tremendous...
06/19/2019

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

Policy gradient (PG) methods are a widely used reinforcement learning me...
07/11/2019

Imitation-Projected Policy Gradient for Programmatic Reinforcement Learning

We present Imitation-Projected Policy Gradient (IPPG), an algorithmic fr...
06/10/2022

Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning

We study policy optimization for Markov decision processes (MDPs) with m...

Please sign up or login with your details

Forgot password? Click here to reset