AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning

Junseok Kim, Dohyeong Kim, Mineui Hong, Songhwai 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 bilinear transduction and dual analogy value/policies (CTA) on top of HIQL∨+α∨ (ablation)CTA · OGBench manipulation averagesuccess rate (%): 39.6 -> 56.3Improved
replace dual goal representation φ(g) with dual analogy α∨(s,g) in HIQL∨, without bilinear transduction (ablation)HIQL∨ · OGBench manipulation averagesuccess rate (%): 39.3 -> 39.6No clear effect
CTA versus dual-goal-representation baselinesCTA · OGBench manipulation averagesuccess rate (%): 39.3 -> 56.3 (HIQL∨)Improved
CTA versus HIQL∨+α∨ on puzzle-4x4 (ablation)CTA · OGBench puzzle-4x4-playsuccess rate (%): 50±5 -> 84±3Improved
CTA versus GCIVL∨ on cube-doubleCTA · OGBench cube-double-playsuccess rate (%): 60±4 -> 50±5Hurt
CTA versus GCIQL on puzzle-3x3CTA · OGBench puzzle-3x3-playsuccess rate (%): 95±1 vs 94±11No clear effect
CTA versus best baselines on puzzle-4x5 and 4x6CTA · OGBench puzzle-4x5/4x6-playsuccess rate (%): 14±1 -> 17±1 (4x5); 12±1 -> 12±2 (4x6)No clear effect
hold out OOC context-task pairs; CTA vs HIQL∨+α∨ on scene (ablation)CTA · scene-play direct OOC case studydirect success rate (%): 48±14 -> 73±9Improved
hold out OOC context-task pairs; CTA vs HIQL∨+α∨ on puzzle-4x4 (ablation)CTA · puzzle-4x4-play direct OOC case studydirect success rate (%): 66±11 -> 80±8Improved
use dual analogy only without bilinear transduction under OOC holdout (HIQL∨ vs HIQL∨+α∨) (ablation)HIQL∨ · scene-play direct OOC case studydirect success rate (%): 45±11 -> 48±14No clear effect
use dual analogy in HIQL∨ on puzzle-4x4 OOC holdout (ablation)HIQL∨ · puzzle-4x4-play direct OOC case studydirect success rate (%): 35±17 -> 66±11Improved
CTA has about 20% fewer parameters than HIQL∨+α∨ yet performs betterCTA · OGBench manipulationsuccess rate (%): about 20% fewer parametersImproved

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