Focused Skill Discovery: Learning To Control Specific State Variables While Minimizing Side Effects

Abstract

Skills are essential for unlocking higher levels of problem solving. A common approach to discovering these skills is to learn ones that reliably reach different states, thus empowering the agent to control its environment. However, existing skill discovery algorithms often overlook the natural state variables present in many reinforcement learning problems, meaning that the discovered skills lack control of specific state variables. This can significantly hamper exploration efficiency, make skills more challenging to learn with, and lead to negative side effects in downstream tasks when the goal is under-specified. We introduce a general method that enables these skill discovery algorithms to learn focused skills -- skills that target and control specific state variables. Our approach improves state space coverage by a factor of three, unlocks new learning capabilities, and automatically avoids negative side effects in downstream tasks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycarr2025focused

Related papers

• Skild: Unsupervised Skill Discovery Guided By Factor Interactions (2024)0.00
• Continual Learning Of Control Primitives: Skill Discovery Via Reset-games (2020)0.00
• Learning More Skills Through Optimistic Exploration (2021)0.00
• Disentangled Unsupervised Skill Discovery For Efficient Hierarchical Reinforcement Learning (2024)0.00
• Skills: Adaptive Skill Sequencing For Efficient Temporally-extended Exploration (2022)0.00
• Autonomous Discovery Of The Goal Space To Learn A Parameterized Skill (2018)0.00
• Learning Transferable Skills In Action Rpgs Via Directed Skill Graphs And Selective Adaptation (2026)0.00
• Neuroevolution Is A Competitive Alternative To Reinforcement Learning For Skill Discovery (2022)0.00