AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

LASER: Learning Active Sensing for Continuum Field Reconstruction

Huayu Deng, Jinghui Zhong, Xiangming Zhu, Yunbo Wang, Xiaokang Yang

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration · 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 GRU history of length 3 vs none (ablation)LASER latent dynamics · NS nu=1e-5 Out-trollout MSE (x1e-1): 5.38 -> 5.23Improved
increase history length from 3 to 5 (ablation)LASER latent dynamics · NS nu=1e-5 Out-trollout MSE (x1e-1): 5.23 -> 7.88Hurt
add history on NS nu=1e-3 Out-t (ablation)LASER latent dynamics · NS nu=1e-3 Out-trollout MSE (x1e-2): 0.822 -> 0.904Hurt
add dynamic quality filtering (ablation)LASER · NS nu=1e-3, 64 sensorsrecon MSE avg (x1e-3): 0.4521 -> 0.4339Improved
add dynamic quality filtering (ablation)LASER · NS nu=1e-3, 256 sensorsrecon MSE avg (x1e-3): 0.3913 -> 0.3024Improved
add sensor displacement (active sensing) over fixed layout (ablation)LASER · NS nu=1e-3, 128 sensorsrecon MSE avg (x1e-3): 0.8180 -> 0.3211Improved
lengthen reward horizon from 1 to 5 (ablation)LASER · NS nu=1e-3, 256 sensors Out-trecon MSE (x1e-3): 0.6136 -> 0.3380Improved
add iterative co-training of world model and policyLASER · SST, 100 sensorsrecon MSE: 0.6932 -> 0.6727Improved
use policy-induced sensors instead of random sensors (ablation)LASER world model · NS nu=1e-3 Out-trollout MSE (x1e-2): 0.971 -> 0.498Improved
replace heuristic sensing (error-based) with learned policy (ablation)LASER · NS nu=1e-3, 64 sensorsrecon MSE (x1e-3): 26.61 -> 0.169Improved
replace PPO with proposed policy optimization (ablation)LASER · NS nu=1e-3, 256 sensorsrecon MSE avg (x1e-3): 0.304 -> 0.302Improved
replace PPO with proposed policy optimization (ablation)LASER · Shallow-Water, 64 sensorsrecon MSE avg (x1e-3): 0.456 -> 0.386Improved

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