Impact of Connectivity on Laplacian Representations in Reinforcement Learning

ArXi:2603.08558v1 Announce Type: new Learning compact state representations in Marko Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories.