InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
This addresses the challenge of mimicking human behavior in domains like autonomous driving, where demonstrations vary due to unmodeled factors, offering an incremental improvement in interpretability and performance over existing methods.
The paper tackles the problem of imitation learning from variable expert demonstrations by proposing InfoGAIL, an unsupervised method that infers latent structure and learns interpretable representations, showing in driving tasks that it accurately reproduces and anticipates human behaviors from visual inputs.
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.