AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis

Yu-Shao Peng, Kai-Fu Tang, Hsuan-Tien Lin, Edward Chang

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards · 41 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 reward shaping and feature rebuilding (ablation)REINFORCE · 200 diseases testtop-5 accuracy: 66.55 -> 79.68Improved
add reward shaping and feature rebuilding (ablation)REINFORCE · 300 diseases testtop-5 accuracy: 31.18 -> 71.17Improved
add reward shaping and feature rebuilding (ablation)REINFORCE · 400 diseases testtop-5 accuracy: 2.09 -> 67.09Improved
add reward shaping alone (ablation)REINFORCE · 200/300/400 diseases trainingtraining accuracy and rewardImproved
add feature rebuilding on top of reward shaping (ablation)RESHAPE · 200/300/400 diseases trainingtraining accuracyImproved
add reward shaping (and rebuilding) to reduce repeated queries (ablation)REINFORCE · 300/400 diseases trainingrepeat rateImproved
use REFUEL instead of hierarchical modelhierarchical model of AAAI 2018 · 73 diseasestop-5 accuracy: 77.94 -> 91.71Improved
use REFUEL instead of hierarchical modelhierarchical model of AAAI 2018 · 255 diseasestop-1 accuracy: 26.26 -> 50.66Improved
REFUEL vs baseline average number of steps (ablation)REINFORCE · 200 diseases#Steps: 6.66 -> 8.01Hurt
REFUEL vs hierarchical model average steps (ablation)hierarchical model · 73 diseases#Steps: 7.15 -> 7.52Hurt

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