Skild: Unsupervised Skill Discovery Guided By Factor Interactions

Abstract

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (Skild), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding Skild is that skills that induce <b>diverse interactions</b> between state factors are often more valuable for solving downstream tasks. To this end, Skild develops a novel skill learning objective that explicitly encourages the ma

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2024skild

Related papers

• Disentangled Unsupervised Skill Discovery For Efficient Hierarchical Reinforcement Learning (2024)0.00
• Focused Skill Discovery: Learning To Control Specific State Variables While Minimizing Side Effects (2025)0.00
• Learning More Skills Through Optimistic Exploration (2021)0.00
• Diversity Is All You Need: Learning Skills Without A Reward Function (2018)0.00
• SKILL0: In-context Agentic Reinforcement Learning For Skill Internalization (2026)0.00
• Leveraging Human Feedback For Semantically-relevant Skill Discovery (2026)0.00
• Hierarchical Cooperative Multi-agent Reinforcement Learning With Skill Discovery (2019)5.24
• Skills: Adaptive Skill Sequencing For Efficient Temporally-extended Exploration (2022)0.00