# DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery

arXiv: https://arxiv.org/abs/2609.17682 · HTML: https://mlsanity.com/paper/2609.17682/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 77 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Provably Efficient Maximum Entropy Exploration](https://mlsanity.com/paper/1812.02690/) (2018)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [Behavior From the Void: Unsupervised Active Pre-Training](https://mlsanity.com/paper/2103.04551/) (2021)
- [Fast Task Inference with Variational Intrinsic Successor Features](https://mlsanity.com/paper/1906.05030/) (2019)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [Learning One Representation to Optimize All Rewards](https://mlsanity.com/paper/2103.07945/) (2021)
- [APS: Active Pretraining with Successor Features](https://mlsanity.com/paper/2108.13956/) (2021)
- [CALM: Conditional Adversarial Latent Models for Directable Virtual Characters](https://mlsanity.com/paper/2305.02195/) (2023)
- [Lipschitz-constrained Unsupervised Skill Discovery](https://mlsanity.com/paper/2202.00914/) (2022)
- [Learning and Transfer of Modulated Locomotor Controllers](https://mlsanity.com/paper/1610.05182/) (2016)
- [Animate3D: Animating Any 3D Model with Multi-view Video Diffusion](https://mlsanity.com/paper/2407.11398/) (2024)
- [Relative Variational Intrinsic Control](https://mlsanity.com/paper/2012.07827/) (2020)

## Abstract (arXiv)

Humans efficiently learn new tasks by reusing a rich repertoire of motor skills across different goals and contexts. A similar strategy can also be used to enable simulated characters to efficiently perform new tasks by leveraging reusable motor skills. To support a wide range of downstream tasks, the learned repertoire should be diverse, consisting of distinct behaviors as well as spatial and temporal variation within each behavior. A commonly used method for learning diverse skills is by maximizing the mutual information between skill latents and the states produced by a policy. The marginal state entropy promotes broad behavioral coverage, while the conditional entropy encourages consistent behaviors from each latent. However, directly estimating the marginal state entropy is intractable in high-dimensional control problems. Prior methods therefore rely on indirect latent-space approximations or coarse estimators of the state distribution. These approximations may not effectively promote broad coverage of the state space, resulting in skills with limited behavioral diversity and reduced utility for downstream tasks. In this work, we propose Diffusion Skill Discovery (DSD), a skill discovery method that uses a diffusion model to approximate the entropy gradient of the policy-induced state distribution through score matching. The resulting objective encourages the discovery of skills that produce a broader range of behaviors for high-dimensional humanoid control. The learned skills are reused in two downstream control settings: hierarchical control with a task-specific high-level policy and zero-shot control through latent selection from offline trajectories. Our experiments show that DSD discovers a broader repertoire of reusable motor skills than prior skill discovery methods, leading to the emergence of complex and agile behaviors that can be reused across downstream tasks.