AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Laplacian Representations for Decision-Time Planning

Dikshant Shehmar, Matthew Kyle Schlegel, Matthew E. Taylor, Marlos C. Machado

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Subgoal generation for hierarchical RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use scaled Laplacian latent space instead of PcLast contrastive latent (no prior)ALPS · Maze2D-PointMass Spiralsuccess rate (%): 35 -> 91 (1 cluster); 60 -> 94 (16 clusters)Improved
use scaled Laplacian latent space instead of PcLast latentALPS · Maze2D-PointMass Roomssuccess rate (%): 30 -> 92 (1 cluster)Improved
add high-level subgoal planner (16 clusters vs 1) to PcLast (ablation)PcLast · Maze2D-PointMass Spiralsuccess rate (%): 35 -> 60Improved
add high-level subgoal planner to ALPS (ablation)ALPS† · Maze2D-PointMass Spiralsuccess rate (%): 91 -> 94No clear effect
add hierarchical Dijkstra subgoal planner (ablation)ALPS · OGBench antmaze-large-exploresuccess rate (%): 1 -> 43 (pi_prior alone vs Dijkstra + pi_prior)Improved
add behavior prior to CEM (ablation)ALPS · OGBench antmaze-large-navigatesuccess rate (%): 0 -> 93 (Dijkstra+CEM vs ALPS)Improved
add behavior prior to CEM (ablation)ALPS · OGBench pointmaze-large-navigatesuccess rate (%): 100 -> 80Hurt
add CEM on top of behavior prior (ablation)ALPS · OGBench antmaze-large-exploresuccess rate (%): 43 -> 90Improved
increase number of clusters in high-level planner (ablation)ALPS · OGBench antmaze-large (varying Kmax/explore data)success rateImproved
use ALPS instead of model-free baselines on giant mazesALPS · OGBench giant mazessuccess rate (%): humanoidmaze-giant-navigate: HIQL 12 -> ALPS 67Improved
use ALPS on teleport mazesALPS · OGBench teleport mazessuccess rate (%): pointmaze-teleport-stitch: HIQL 34 vs ALPS 13Mixed
use ALPS on multi-cube manipulationALPS · OGBench cube-double-playsuccess rate (%): 68 (single) -> 2 (double)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy