Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2602.09767 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911437761282048 |
|---|---|
| author | Cui, Ruopeng Bi, Yifei Luo, Haojie Li, Wei |
| author_facet | Cui, Ruopeng Bi, Yifei Luo, Haojie Li, Wei |
| contents | Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these burdens by learning a diverse repertoire of useful skills driven by intrinsic motivation. However, existing methods exhibit two key limitations: they typically rely on a single policy to master a versatile repertoire of behaviors without modeling the shared structure or distinctions among them, which results in low learning efficiency; moreover, they are susceptible to reward hacking, where the reward signal increases and converges rapidly while the learned skills display insufficient actual diversity. In this work, we introduce an Orthogonal Mixture-of-Experts (OMoE) architecture that prevents diverse behaviors from collapsing into overlapping representations, enabling a single policy to master a wide spectrum of locomotion skills. In addition, we design a multi-discriminator framework in which different discriminators operate on distinct observation spaces, effectively mitigating reward hacking. We evaluated our method on the 12-DOF Unitree A1 quadruped robot, demonstrating a diverse set of locomotion skills. Our experiments demonstrate that the proposed framework boosts training efficiency and yields an 18.3\% expansion in state-space coverage compared to the baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09767 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diverse Skill Discovery for Quadruped Robots via Unsupervised Learning Cui, Ruopeng Bi, Yifei Luo, Haojie Li, Wei Robotics Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these burdens by learning a diverse repertoire of useful skills driven by intrinsic motivation. However, existing methods exhibit two key limitations: they typically rely on a single policy to master a versatile repertoire of behaviors without modeling the shared structure or distinctions among them, which results in low learning efficiency; moreover, they are susceptible to reward hacking, where the reward signal increases and converges rapidly while the learned skills display insufficient actual diversity. In this work, we introduce an Orthogonal Mixture-of-Experts (OMoE) architecture that prevents diverse behaviors from collapsing into overlapping representations, enabling a single policy to master a wide spectrum of locomotion skills. In addition, we design a multi-discriminator framework in which different discriminators operate on distinct observation spaces, effectively mitigating reward hacking. We evaluated our method on the 12-DOF Unitree A1 quadruped robot, demonstrating a diverse set of locomotion skills. Our experiments demonstrate that the proposed framework boosts training efficiency and yields an 18.3\% expansion in state-space coverage compared to the baseline. |
| title | Diverse Skill Discovery for Quadruped Robots via Unsupervised Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.09767 |