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. Results are best visualized through https://jiashunwang.github.io/HIL

翻译：基于深度强化学习的数据驱动方法已成为开发控制器的主流范式，使物理仿真角色能够产生自然类人行为。然而，这些数据驱动方法常难以适应新环境，并组合多样化技能以执行更复杂的交互任务。为解决这些挑战，我们提出混合模仿学习框架，结合运动跟踪精确复现技能与对抗模仿学习增强适应性和技能组合能力，从而实现高动态行为鲁棒控制。该混合学习框架通过并行多任务环境和统一观测空间实现，利用目标条件表征促进混合并行环境间的知识共享。我们通过跑酷式障碍穿越任务和航向控制任务验证了HIL的有效性。该统一控制器不仅保留参考运动数据的自然性，还能有效泛化至挑战性新环境。在程序生成任务与基线方法的对比评估表明，我们的方法提升了运动质量、增加了技能多样性，并在任务完成率方面取得了具有竞争力的表现。最佳效果可参阅 https://jiashunwang.github.io/HIL