Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This problem is critical in applications like robotics, where modeling multiple valid actions ensures both performance and safety. We propose EBGAN-MDN, a framework that integrates energy-based models, Mixture Density Networks (MDNs), and adversarial training. By leveraging a modified InfoNCE loss and an energy-enforced MDN loss, EBGAN-MDN effectively addresses these challenges. Experiments on synthetic and robotic benchmarks demonstrate superior performance, establishing EBGAN-MDN as a effective and efficient solution for multi-modal learning tasks.
@article{arxiv.2510.07562,
title = {EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning},
author = {Yixiao Li and Julia Barth and Thomas Kiefer and Ahmad Fraij},
journal= {arXiv preprint arXiv:2510.07562},
year = {2025}
}