Guiding Skill Discovery with Foundation Models

• URL: http://arxiv.org/abs/2510.23167v1
• Date: Mon, 27 Oct 2025 09:47:40 GMT
• Title: Guiding Skill Discovery with Foundation Models
• Authors: Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat, Vincent François-Lavet, Edward S. Hu,
• Abstract summary: existing skill discovery methods focus solely on maximizing the diversity of skills without considering human preferences.<n>We propose a Foundation model Guided (FoG) skill discovery method, which incorporates human intentions into skill discovery.<n>FoG successfully learns to eliminate undesirable behaviors, such as flipping or rolling, and to avoid hazardous areas in both state-based and pixel-based tasks.
• Score: 8.41850245020636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on maximizing the diversity of skills without considering human preferences, which leads to undesirable behaviors and possibly dangerous skills. For instance, a cheetah robot trained using previous methods learns to roll in all directions to maximize skill diversity, whereas we would prefer it to run without flipping or entering hazardous areas. In this work, we propose a Foundation model Guided (FoG) skill discovery method, which incorporates human intentions into skill discovery through foundation models. Specifically, FoG extracts a score function from foundation models to evaluate states based on human intentions, assigning higher values to desirable states and lower to undesirable ones. These scores are then used to re-weight the rewards of skill discovery algorithms. By optimizing the re-weighted skill discovery rewards, FoG successfully learns to eliminate undesirable behaviors, such as flipping or rolling, and to avoid hazardous areas in both state-based and pixel-based tasks. Interestingly, we show that FoG can discover skills involving behaviors that are difficult to define. Interactive visualisations are available from https://sites.google.com/view/submission-fog.

Related papers

• Efficient Skill Discovery via Regret-Aware Optimization [37.27136009415794]
  We frame skill discovery as a min-max game of skill generation and policy learning.<n>We propose a regret-aware method on top of temporal representation learning.<n>Our method achieves a 15% zero shot improvement in high-dimensional environments.
  arXiv  Detail & Related papers  (2025-06-26T06:45:59Z)
• Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment [14.948610521764415]
  We propose Human-aligned Skill Discovery (HaSD) to discover safer, more aligned skills.<n>HaSD simultaneously optimises skill diversity and alignment with human values.<n>We demonstrate its effectiveness in both 2D navigation and SafetyGymnasium environments.
  arXiv  Detail & Related papers  (2025-01-29T06:14:27Z)
• Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning [39.991887534269445]
  Disentangled Unsupervised Skill Discovery (DUSDi) is a method for learning disentangled skills that can be efficiently reused to solve downstream tasks. DUSDi decomposes skills into disentangled components, where each skill component only affects one factor of the state space. DUSDi successfully learns disentangled skills, and significantly outperforms previous skill discovery methods when it comes to applying the learned skills to solve downstream tasks.
  arXiv  Detail & Related papers  (2024-10-15T04:13:20Z)
• SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution [75.2573501625811]
  Diffusion models have demonstrated strong potential for robotic trajectory planning. generating coherent trajectories from high-level instructions remains challenging. We propose SkillDiffuser, an end-to-end hierarchical planning framework.
  arXiv  Detail & Related papers  (2023-12-18T18:16:52Z)
• Behavior Contrastive Learning for Unsupervised Skill Discovery [75.6190748711826]
  We propose a novel unsupervised skill discovery method through contrastive learning among behaviors. Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill. Our method implicitly increases the state entropy to obtain better state coverage.
  arXiv  Detail & Related papers  (2023-05-08T06:02:11Z)
• Choreographer: Learning and Adapting Skills in Imagination [60.09911483010824]
  We present Choreographer, a model-based agent that exploits its world model to learn and adapt skills in imagination. Our method decouples the exploration and skill learning processes, being able to discover skills in the latent state space of the model. Choreographer is able to learn skills both from offline data, and by collecting data simultaneously with an exploration policy.
  arXiv  Detail & Related papers  (2022-11-23T23:31:14Z)
• Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics [18.546688182454236]
  Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. We propose accelerating exploration in the skill space using state-conditioned generative models. We validate our approach across four challenging manipulation tasks, demonstrating our ability to learn across task variations.
  arXiv  Detail & Related papers  (2022-11-04T02:42:17Z)
• Lipschitz-constrained Unsupervised Skill Discovery [91.51219447057817]
  Lipschitz-constrained Skill Discovery (LSD) encourages the agent to discover more diverse, dynamic, and far-reaching skills. LSD outperforms previous approaches in terms of skill diversity, state space coverage, and performance on seven downstream tasks.
  arXiv  Detail & Related papers  (2022-02-02T08:29:04Z)
• Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback [82.96694147237113]
  We present Skill Preferences, an algorithm that learns a model over human preferences and uses it to extract human-aligned skills from offline data. We show that SkiP enables a simulated kitchen robot to solve complex multi-step manipulation tasks.
  arXiv  Detail & Related papers  (2021-08-11T18:04:08Z)
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning [81.12201426668894]
  We develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks. We show that our proposed algorithm provides substantial improvement in learning efficiency, making reward-free real-world training feasible. We also demonstrate that the learned skills can be composed using model predictive control for goal-oriented navigation, without any additional training.
  arXiv  Detail & Related papers  (2020-04-27T17:38:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.