Proper Laplacian Representation Learning

Abstract

The ability to learn good representations of states is essential for solving large reinforcement learning problems, where exploration, generalization, and transfer are particularly challenging. The Laplacian representation is a promising approach to address these problems by inducing informative state encoding and intrinsic rewards for temporally-extended action discovery and reward shaping. To obtain the Laplacian representation one needs to compute the eigensystem of the graph Laplacian, which is often approximated through optimization objectives compatible with deep learning approaches. These approximations, however, depend on hyperparameters that are impossible to tune efficiently, converge to arbitrary rotations of the desired eigenvectors, and are unable to accurately recover the corresponding eigenvalues. In this paper we introduce a theoretically sound objective and corresponding optimization algorithm for approximating the Laplacian representation. Our approach naturally recov

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygomez2023proper

Related papers

• Temporal Abstractions-augmented Temporally Contrastive Learning: An Alternative To The Laplacian In RL (2022)0.00
• The Laplacian Keyboard: Beyond The Linear Span (2026)0.00
• On The Generalization Of Representations In Reinforcement Learning (2022)0.00
• Extracting Latent State Representations With Linear Dynamics From Rich Observations (2020)0.00
• A Survey Of State Representation Learning For Deep Reinforcement Learning (2025)0.00
• Visual Processing In Context Of Reinforcement Learning (2022)0.00
• Locally Constrained Representations In Reinforcement Learning (2022)0.00
• Understanding Self-predictive Learning For Reinforcement Learning (2022)0.00