AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Benchmarking Reinforcement Learning Algorithms for ICU Ventilator Settings: An Interpretable and Probabilistic Patient Environment for Doctor Agents

Ya-Hsi Chang, Po-Chih Kuo

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 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 action-stability penalty (ablation)NFQ · Medium severity, MIMIC testaverage reward: 8.49 -> 8.64 when removedHurt
add action-stability penalty (ablation)NFQ · High severity, MIMIC testtime to meet extubation guidelines: 16.46 -> 16.29 hours when removedHurt
add intermediate state rewards (ablation)CQL · High severity, MIMIC testtrajectory length: 15.46 vs. 18.33Hurt
add intermediate state rewards (ablation)CQL · High severity, MIMIC testtime to meet: 16.19 vs. 19.92Hurt
add intermediate state rewards (ablation)CQL · High severity, eICU OOD testtrajectory length: 17.58 vs. 22.32Hurt
add intermediate state rewards (ablation)CQL · High severity, eICU OOD testtime to meet: 18.6 vs. 23.41Hurt
add terminal extubation reward (ablation)CQL and BCQ · eICU OOD testaction diversityHurt
raise terminal extubation reward from 10 to 100 (ablation)DQN · High severity, MIMIC testtrajectory length: 16.76 -> 15.39Improved
raise terminal extubation reward from 10 to 100 (ablation)DQN · High severity, MIMIC testtime to meet: 17.15 -> 15.99Improved
raise terminal extubation reward from 10 to 100 (ablation)agents (DQN, DDQN, BCQ, CQL) · Test and OOD testextubation meet rateHurt
use offline RL agents instead of physician policyDDQN · High severity, MIMIC testextubation meet rate: 39.0 -> 95.0Improved
use offline RL agents instead of physician policyDDQN · High severity, MIMIC testtime to meet: 55.41 -> 16.02Improved

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