Inverse Reinforcement Learning without Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Swamy, Gokul, Choudhury, Sanjiban, Bagnell, J. Andrew, Wu, Zhiwei Steven
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911767086497792
author Swamy, Gokul
Choudhury, Sanjiban
Bagnell, J. Andrew
Wu, Zhiwei Steven
author_facet Swamy, Gokul
Choudhury, Sanjiban
Bagnell, J. Andrew
Wu, Zhiwei Steven
contents Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational weakness: they require repeatedly solving a hard reinforcement learning (RL) problem as a subroutine. This is counter-intuitive from the viewpoint of reductions: we have reduced the easier problem of imitation learning to repeatedly solving the harder problem of RL. Another thread of work has proved that access to the side-information of the distribution of states where a strong policy spends time can dramatically reduce the sample and computational complexities of solving an RL problem. In this work, we demonstrate for the first time a more informed imitation learning reduction where we utilize the state distribution of the expert to alleviate the global exploration component of the RL subroutine, providing an exponential speedup in theory. In practice, we find that we are able to significantly speed up the prior art on continuous control tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2303_14623
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inverse Reinforcement Learning without Reinforcement Learning
Swamy, Gokul
Choudhury, Sanjiban
Bagnell, J. Andrew
Wu, Zhiwei Steven
Machine Learning
Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational weakness: they require repeatedly solving a hard reinforcement learning (RL) problem as a subroutine. This is counter-intuitive from the viewpoint of reductions: we have reduced the easier problem of imitation learning to repeatedly solving the harder problem of RL. Another thread of work has proved that access to the side-information of the distribution of states where a strong policy spends time can dramatically reduce the sample and computational complexities of solving an RL problem. In this work, we demonstrate for the first time a more informed imitation learning reduction where we utilize the state distribution of the expert to alleviate the global exploration component of the RL subroutine, providing an exponential speedup in theory. In practice, we find that we are able to significantly speed up the prior art on continuous control tasks.
title Inverse Reinforcement Learning without Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2303.14623