Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations

Huiqiao Fu, Kaiqiang Tang, Yuanyang Lu, Yiming Qi, Guizhou Deng, Flood Sung, Chunlin Chen

Keywords: Generative adversarial imitation learning, semi-supervised learning, multi-modal behaviors, imbalanced data

TL;DR: We enhance InfoGAIL by introducing a semi-supervised architecture that specifically tackles the challenge of learning multi-modal behaviors within imbalanced demonstrations.

Abstract: Imitation learning aims to reproduce expert behaviors without relying on an explicit reward signal. However, real-world demonstrations often present challenges, such as multi-modal, data imbalance, and expensive labeling processes. In this work, we propose a novel semi-supervised imitation learning architecture that learns disentangled behavior representations from imbalanced demonstrations using limited labeled data. Specifically, our method consists of three key components. First, we adapt the concept of semi-supervised generative adversarial networks to the imitation learning context. Second, we employ a learnable latent distribution to align the generated and expert data distributions. Finally, we utilize a regularized information maximization approach in conjunction with an approximate label prior to further improve the semi-supervised learning performance. Experimental results demonstrate the efficiency of our method in learning multi-modal behaviors from imbalanced demonstrations compared to baseline methods.

Submission Number: 14092