AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data

Hyunwoo Park, Sanghyun Lee

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 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
replace CODAS with AIDA (adaptive imagination + self-consistency)CODAS · HalfCheetahreturn ratio: 0.711 -> 0.810Improved
replace CODAS with AIDACODAS · Hopperreturn ratio: 0.356 -> 0.440Improved
replace CODAS with AIDACODAS · InvertedPendulumreturn ratio: 0.440 -> 0.561Improved
replace CODAS with AIDACODAS · Walker2dRMSE: 2.180 -> 1.784Improved
replace CODAS with AIDACODAS · Walker2dreturn ratio: 0.038 -> 0.058Hurt
replace CODAS with AIDACODAS · InvertedPendulumRMSE: 0.108 -> 0.075Improved
replace CODAS with AIDA with fewer target dataCODAS · HalfCheetah (10 target trajectories)return ratio: 0.058 -> 0.175Improved
replace CODAS with AIDA at 30 trajectoriesCODAS · HalfCheetah (30 target trajectories)return ratio: 0.476 -> 0.573Improved
use adaptive horizon instead of fixed horizons K in {0,5,10,20} (ablation)AIDA · HopperreturnImproved
add imagination with a fixed horizon (ablation)AIDA · HopperreturnNo clear effect
add self-consistency loss on imagined transitions (ablation)AIDA · InvertedPendulumdecoded pendulum angle fidelityImproved
add online-interacting PAD instead of offline AIDAPAD · seven tasksreturn ratioHurt

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