AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models

Minting Pan, Xiangming Zhu, Yunbo Wang, Xiaokang Yang

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 6 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
remove action-free branch (ablation)Iso-Dream · BAIR bouncing balls, predict 18 framesPSNR: 21.43 -> 20.47Hurt
remove action-free branch (ablation)Iso-Dream · BAIR bouncing balls, predict 28 framesPSNR: 19.51 -> 18.51Hurt
remove action-free branch (ablation)Iso-Dream · BAIR bouncing balls, predict 28 framesSSIM: 0.768 -> 0.690Hurt
remove Inverse cell (ablation)Iso-Dream · BAIR bouncing balls, predict 18 framesPSNR: 21.43 -> 21.42No clear effect
remove Inverse cell (ablation)Iso-Dream · BAIR bouncing balls, predict 28 framesPSNR: 19.51 -> 19.34Hurt
remove Inverse cell (ablation)Iso-Dream · BAIR bouncing balls, predict 28 framesSSIM: 0.768 -> 0.759Hurt
remove Inverse cell (ablation)Iso-Dream · CARLAepisode returnHurt
concatenate controllable and noncontrollable states directly instead of rolling out noncontrollable states with attention (ablation)Iso-Dream policy · CARLAepisode returnHurt
remove separate network branch for static time-invariant information (ablation)Iso-Dream · CARLAepisode return: about 15%Hurt
replace DreamerV2 with Iso-DreamDMC video_easy agent · Walker walkfinal return: 655 $\pm$ 47 -> 911 $\pm$ 50Improved
replace DreamerV2 with Iso-DreamDMC video_easy agent · hopper standfinal return: 260 $\pm$ 366 -> 746 $\pm$ 312Improved
replace SVG with Iso-Dreamvideo predictor · BAIR bouncing ballsPSNR: 18.12 -> 19.51Improved

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