# Learning and Exploring Motor Skills with Spacetime Bounds

arXiv: https://arxiv.org/abs/2103.16807 · HTML: https://mlsanity.com/paper/2103.16807/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2021.

## Built on by (most cited first, 9 of 9)

- [DiffMimic: Efficient Motion Mimicking with Differentiable Physics](https://mlsanity.com/paper/2304.03274/) (2023)
- [Discovering Diverse Athletic Jumping Strategies](https://mlsanity.com/paper/2105.00371/) (2021)
- [A Survey on Reinforcement Learning Methods in Character Animation](https://mlsanity.com/paper/2203.04735/) (2022)
- [Physics-Based Motion Imitation with Adversarial Differential Discriminators](https://mlsanity.com/paper/2505.04961/) (2025)
- [Learning to Get Up](https://mlsanity.com/paper/2205.00307/) (2022)
- [Efficient Hyperparameter Optimization for Physics-based Character Animation](https://mlsanity.com/paper/2104.12365/) (2021)
- [An Adaptable Approach to Learn Realistic Legged Locomotion without Examples](https://mlsanity.com/paper/2110.14998/) (2021)
- [Complex Locomotion Skill Learning via Differentiable Physics](https://mlsanity.com/paper/2206.02341/) (2022)
- [Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation](https://mlsanity.com/paper/2306.08224/) (2023)

## Abstract (arXiv)

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