ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2505.21410
21
0

MRSD: Multi-Resolution Skill Discovery for HRL Agents

27 May 2025
Shashank Sharma
Janina Hoffmann
Vinay P. Namboodiri
ArXiv (abs)PDFHTML
Main:9 Pages
19 Figures
Bibliography:2 Pages
2 Tables
Appendix:16 Pages
Abstract

Hierarchical reinforcement learning (HRL) relies on abstract skills to solve long-horizon tasks efficiently. While existing skill discovery methods learns these skills automatically, they are limited to a single skill per task. In contrast, humans learn and use both fine-grained and coarse motor skills simultaneously. Inspired by human motor control, we propose Multi-Resolution Skill Discovery (MRSD), an HRL framework that learns multiple skill encoders at different temporal resolutions in parallel. A high-level manager dynamically selects among these skills, enabling adaptive control strategies over time. We evaluate MRSD on tasks from the DeepMind Control Suite and show that it outperforms prior state-of-the-art skill discovery and HRL methods, achieving faster convergence and higher final performance. Our findings highlight the benefits of integrating multi-resolution skills in HRL, paving the way for more versatile and efficient agents.

View on arXiv
@article{sharma2025_2505.21410,
  title={ MRSD: Multi-Resolution Skill Discovery for HRL Agents },
  author={ Shashank Sharma and Janina Hoffmann and Vinay Namboodiri },
  journal={arXiv preprint arXiv:2505.21410},
  year={ 2025 }
}
Comments on this paper