Generative Adversarial Imitation from Observation

TL;DR

This paper introduces GAIfO, a generative adversarial network-based method for imitation from observation, enabling agents to learn from state-only demonstrations, including raw visual data, with performance comparable or superior to existing methods.

Contribution

The paper presents a novel GAN-based framework for imitation from observation and demonstrates its effectiveness in both low-dimensional and high-dimensional environments.

Findings

GAIfO performs comparably to action-based imitation methods.

GAIfO outperforms existing IfO methods in high-dimensional settings.

Effective learning from raw visual demonstrations.

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.