Learning and Exploring Motor Skills with Spacetime Bounds

2021/03/31 by Like Ma, Zeshi Yang, Ma, Li-Ke +7
Computer Science · Engineering · #FOS: Computer and information sciences #Graphics (cs.GR) #Human Motion and Animation #Human Pose and Action Recognition #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.2103.16807

openalex publication_date 2021/03/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Equipping characters with diverse motor skills is the current bottleneck of physics-based character animation. We propose a Deep Reinforcement Learning (DRL) framework that enables physics-based characters to learn and explore motor skills from reference motions. The key insight is to use loose space-time constraints, termed spacetime bounds, to limit the search space in an early termination fashion. As we only rely on the reference to specify loose spacetime bounds, our learning is more robust with respect to low quality references. Moreover, spacetime bounds are hard constraints that improve learning of challenging motion segments, which can be ignored by imitation-only learning. We compare our method with state-of-the-art tracking-based DRL methods. We also show how to guide style exploration within the proposed framework

Citations

• Continuous control with deep reinforcement learning
• Phase-functioned neural networks for character control
• Emergence of Locomotion Behaviours in Rich Environments

Related

• DeepMimic
• SFV: Reinforcement Learning of Physical Skills from Videos
• Neural Categorical Priors for Physics-Based Character Control
• SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
• Efficient Hyperparameter Optimization for Physics-based Character Animation