The Laplacian Keyboard: Beyond The Linear Span

Abstract

Across scientific disciplines, Laplacian eigenvectors serve as a fundamental basis for simplifying complex systems, from signal processing to quantum mechanics. In reinforcement learning (RL), these eigenvectors provide a natural basis for approximating reward functions; however, their use is typically limited to their linear span, which restricts expressivity in complex environments. We introduce the Laplacian Keyboard (LK), a hierarchical framework that goes beyond the linear span. LK constructs a task-agnostic library of options from these eigenvectors, forming a behavior basis guaranteed to contain the optimal policy for any reward within the linear span. A meta-policy learns to stitch these options dynamically, enabling efficient learning of policies outside the original linear constraints. We establish theoretical bounds on zero-shot approximation error and demonstrate empirically that LK surpasses zero-shot solutions while achieving improved sample efficiency compared to standar

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychandrasekar2026the

Related papers

• Proper Laplacian Representation Learning (2023)0.00
• Temporal Abstractions-augmented Temporally Contrastive Learning: An Alternative To The Laplacian In RL (2022)0.00
• Model-free Low-rank Reinforcement Learning Via Leveraged Entry-wise Matrix Estimation (2024)0.00
• Representation Of Reinforcement Learning Policies In Reproducing Kernel Hilbert Spaces (2020)0.00
• Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity (2021)0.00
• Spectral Representation-based Reinforcement Learning (2025)0.00
• Response-level Rewards Are All You Need For Online Reinforcement Learning In Llms: A Mathematical Perspective (2025)0.00
• Multilinear Tensor Low-rank Approximation For Policy-gradient Methods In Reinforcement Learning (2025)0.00