InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations

TL;DR

This paper introduces InfoGAIL, an imitation learning algorithm that infers interpretable latent structures from visual demonstrations, enabling accurate behavior imitation and understanding of complex human actions without explicit rewards.

Contribution

It presents a novel unsupervised method based on GANs that learns interpretable representations from visual data in imitation learning tasks.

Findings

Successfully reproduces diverse behaviors from human demonstrations.

Learns meaningful latent factors that capture semantic variations.

Outperforms baselines in capturing underlying structure of demonstrations.

Abstract

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not explicitly modeled. In this paper, we propose a new algorithm that can infer the latent structure of expert demonstrations in an unsupervised way. Our method, built on top of Generative Adversarial Imitation Learning, can not only imitate complex behaviors, but also learn interpretable and meaningful representations of complex behavioral data, including visual demonstrations. In the driving domain, we show that a model learned from human demonstrations is able to both accurately reproduce a variety of behaviors and accurately anticipate human actions using raw visual inputs. Compared with various baselines, our method can better capture the latent structure underlying expert demonstrations, often recovering semantically meaningful factors of variation in the data.