AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation

Naoki Morihira, Amal Nahar, Kartik Bharadwaj, Yasuhiro Kato, Akinobu Hayashi, Tatsuya Harada

ICLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 4 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 image decoder reconstruction loss with Barlow Twins redundancy-reduction lossDreamerV3 · DMC Walker Walktraining time (hours): 7.0 -> 4.4 (1.59x speedup)Improved
use redundancy reduction instead of DA-based DreamerProDreamerPro · DMC Walker Walktraining time (hours): 10.4 -> 4.4 (2.36x speedup)Improved
add random-shift data augmentation to R2-Dreamer (ablation)R2-Dreamer · 20 DMC tasks (mean/median)task scoreNo clear effect
remove data augmentation from DreamerPro (ablation)DreamerPro · 20 DMC taskstask scoreHurt
halve batch size (B=16 to B=8) (ablation)R2-Dreamer · 20 DMC taskstask score: B=16 -> B=8No clear effect
add random-shift data augmentation to R2-Dreamer (ablation)R2-Dreamer · DMC-Subtle (5 tasks)task scoreHurt
use R2-Dreamer instead of DreamerV3, DreamerPro, TD-MPC2, DrQ-v2R2-Dreamer · DMC-Subtle (5 tasks)task scoreImproved
use R2-Dreamer instead of baselinesR2-Dreamer · 20 DMC tasks and Meta-World MT1 (50 tasks)mean/median score or success rateNo clear effect

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