Laplacian Representations for Decision-Time Planning

ArXi:2602.05031v2 Announce Type: replace Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations are critical as they must local cost computation while preserving long-horizon structure. In this paper, we show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales.