HIL: Hybrid Imitation Learning for Dynamic Athletic Control
ACM Transactions on Graphics (TOG 2026)
Jiashun Wang (1)Yifeng Jiang (2)Haotian Zhang (2)Chen Tessler (2)Davis Rempe (2)Jessica Hodgins (1)Xue Bin Peng (2, 3)
(1) Carnegie Mellon University (2) NVIDIA (3) Simon Fraser University
Abstract
Data-driven methods leveraging deep reinforcement learning have
become the dominant paradigm for developing controllers that
enable physically simulated characters to produce natural
human-like behaviors. However, these data-driven methods often
struggle to adapt to novel environments and compose diverse
skills to perform more complex interaction tasks with the
environment. To address these challenges, we propose a hybrid
imitation learning (HIL) framework that combines motion
tracking, for precise skill replication, with adversarial
imitation learning, to enhance adaptability and skill
composition, enabling robust dynamic control for highly
athletic behaviors. This hybrid learning framework is
implemented through parallel multi-task environments and a
unified observation space, utilizing a goal-conditioned
representation to facilitate knowledge-sharing across the
hybrid parallel environments. We demonstrate the
effectiveness of HIL on a parkour-style obstacle traversal
task and a heading control task. Our framework enables a
unified controller that not only preserves the naturalness
of reference motion data, but also generalizes effectively
to challenging new environments. Evaluations across
procedurally generated tasks and baselines show that our
method improves motion quality, increases skill diversity,
and achieves competitive task completion compared to
previous learning-based approaches.
@article{
wang2026hil,
title={HIL: Hybrid Imitation Learning for Dynamic Athletic Control},
author={Wang, Jiashun and Jiang, Yifeng and Zhang, Haotian and Tessler, Chen and Rempe, Davis and Hodgins, Jessica and Peng, Xue Bin},
journal={ACM Trans. Graph.},
year={2026}
}
