Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Generative Adversarial Imitation from Observation

Faraz Torabi, Garrett Warnell, and Peter Stone. Generative Adversarial Imitation from Observation. In Imitation, Intent, and Interaction (I3) Workshop at ICML 2019, June 2019.

Download

[PDF]1.0MB  

Abstract

Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions.The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from a large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and also a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We conduct experiments in two different settings: (1) when demonstrations consist of low-dimensional, manually-defined state features, and (2) when demonstrations consist of high-dimensional, raw visual data. We demonstrate that our approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.

BibTeX Entry

@InProceedings{ICML19a-torabi,
  author = {Faraz Torabi and Garrett Warnell and Peter Stone},
  title = {Generative Adversarial Imitation from Observation},
  booktitle = {Imitation, Intent, and Interaction (I3) Workshop at ICML 2019},
  location = {Long Beach, California, USA},
  month = {June},
  year = {2019},
  abstract = {
Imitation from observation (IfO) is the problem of learning directly from 
state-only demonstrations without having access to the demonstrator's actions.
The lack of action information both distinguishes IfO from most of the 
literature in imitation learning, and also sets it apart as a method that may 
enable agents to learn from a large set of previously inapplicable resources 
such as internet videos. In this paper, we propose both a general framework 
for IfO approaches and also a new IfO approach based on generative adversarial 
networks called generative adversarial imitation from observation (GAIfO). We 
conduct experiments in two different settings: (1) when demonstrations consist 
of low-dimensional, manually-defined state features, and (2) when 
demonstrations consist of high-dimensional, raw visual data. We demonstrate 
that our approach performs comparably to classical imitation learning 
approaches (which have access to the demonstrator's actions) and significantly 
outperforms existing imitation from observation methods in high-dimensional 
simulation environments.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Nov 24, 2020 14:00:06