AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning

Hyungkyu Kang, Byeongchan Kim, Min-hwan Oh

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 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
add continuity regularization (ablation)LAVL · pointmaze-giantsuccess rate (%): 35% -> 95%Improved
add continuity regularization (ablation)LAVL · antmaze-giant and scenesuccess rateImproved
vary latent dimension from 16 to 256 (ablation)LAVL · OGBenchsuccess rateNo clear effect
use LAN value architecture instead of IQE, MRN or Hilbert (ablation)LAVL · scenesuccess rate: 88% vs below 20%Improved
use LAN instead of MLP value (HIQL baseline) (ablation)LAVL · scenesuccess rate: below 40% -> 88%Improved
use IQE, MRN or Hilbert instead of MLP value (ablation)LAVL · antmaze-giantsuccess rateImproved
replace HIQL high-level value with LAVL-HV separate high-level value (ablation)HIQL · two maze datasetssuccess rate: nearly 0% -> over 80%Improved
use unitary LAVL value instead of separate high/low-level values (LAVL-HV) (ablation)LAVL · OGBenchsuccess rateImproved
use LAVL instead of HIQLHIQL · maze giant averagesuccess rate (%): 21 -> 85Improved
use LAVL instead of OTA on humanoidmaze-giant-navigateOTA · humanoidmaze giant-navigatesuccess rate (%): 92 -> 83Hurt
use LAN instead of MLP in GCXVL (ablation)GCXVL · Antmaze-large-navigate, beta 3success rate (%): 17 -> 54Improved
use LAN instead of MLP in GCXVL (ablation)GCXVL · Cube-single-play, beta 1success rate (%): 24 -> 5Hurt

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