From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity

Luca Grillotti, Lisa Coiffard, Oscar Pang, Maxence Faldor, Antoine Cully
Proceedings of The 9th Conference on Robot Learning, PMLR 305:2519-2535, 2025.

Abstract

Autonomous skill discovery aims to enable robots to acquire diverse be-haviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing methods, including Quality-Diversity Actor-Critic (QDAC), require manually defined skill spaces and carefully tuned heuristics, limiting real-world applicability. We propose Unsupervised Real-world Skill Acquisition (URSA), an extension of QDAC that enables robots to autonomously discover and master diverse, high-performing skills directly in the real world. We demonstrate that URSA successfully discovers diverse locomotion skills on a Unitree A1 quadruped in both simulation and the real world. Our approach supports both heuristic-driven skill discovery and fully unsupervised settings. We also show that the learn skill repertoire can be reused for downstream tasks such as real-world damage adaptation, where URSA outperforms all baselines in 5 out of 9 simulated and 3 out of 5 real-world damage scenarios. Our results establish a new framework for real-world robot learning that enables continuous skill discovery with limited human intervention, representing a significant step toward more autonomous and adaptable robotic systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-grillotti25a, title = {From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity}, author = {Grillotti, Luca and Coiffard, Lisa and Pang, Oscar and Faldor, Maxence and Cully, Antoine}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {2519--2535}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/grillotti25a/grillotti25a.pdf}, url = {https://proceedings.mlr.press/v305/grillotti25a.html}, abstract = {Autonomous skill discovery aims to enable robots to acquire diverse be-haviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing methods, including Quality-Diversity Actor-Critic (QDAC), require manually defined skill spaces and carefully tuned heuristics, limiting real-world applicability. We propose Unsupervised Real-world Skill Acquisition (URSA), an extension of QDAC that enables robots to autonomously discover and master diverse, high-performing skills directly in the real world. We demonstrate that URSA successfully discovers diverse locomotion skills on a Unitree A1 quadruped in both simulation and the real world. Our approach supports both heuristic-driven skill discovery and fully unsupervised settings. We also show that the learn skill repertoire can be reused for downstream tasks such as real-world damage adaptation, where URSA outperforms all baselines in 5 out of 9 simulated and 3 out of 5 real-world damage scenarios. Our results establish a new framework for real-world robot learning that enables continuous skill discovery with limited human intervention, representing a significant step toward more autonomous and adaptable robotic systems.} }
Endnote
%0 Conference Paper %T From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity %A Luca Grillotti %A Lisa Coiffard %A Oscar Pang %A Maxence Faldor %A Antoine Cully %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-grillotti25a %I PMLR %P 2519--2535 %U https://proceedings.mlr.press/v305/grillotti25a.html %V 305 %X Autonomous skill discovery aims to enable robots to acquire diverse be-haviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing methods, including Quality-Diversity Actor-Critic (QDAC), require manually defined skill spaces and carefully tuned heuristics, limiting real-world applicability. We propose Unsupervised Real-world Skill Acquisition (URSA), an extension of QDAC that enables robots to autonomously discover and master diverse, high-performing skills directly in the real world. We demonstrate that URSA successfully discovers diverse locomotion skills on a Unitree A1 quadruped in both simulation and the real world. Our approach supports both heuristic-driven skill discovery and fully unsupervised settings. We also show that the learn skill repertoire can be reused for downstream tasks such as real-world damage adaptation, where URSA outperforms all baselines in 5 out of 9 simulated and 3 out of 5 real-world damage scenarios. Our results establish a new framework for real-world robot learning that enables continuous skill discovery with limited human intervention, representing a significant step toward more autonomous and adaptable robotic systems.
APA
Grillotti, L., Coiffard, L., Pang, O., Faldor, M. & Cully, A.. (2025). From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:2519-2535 Available from https://proceedings.mlr.press/v305/grillotti25a.html.

Related Material