AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Jump Interval-Learning for Individualized Decision Making with Continuous Treatments

Hengrui Cai, Chengchun Shi, Rui Song, Wenbin Lu

JMLR 2023 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL

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
use deep neural network (D-JIL) instead of linear model (L-JIL)JIL · Scenario 3 (p=20, n=800)value function: 0.511 -> 0.545Improved
use linear model (L-JIL) instead of deep network (D-JIL)JIL · Scenario 1 (p=20, n=800)value function: 1.138 -> 1.297Improved
replace outcome-weighted learning (L-O-L) with L-JILL-O-L · Scenario 4 (p=20, n=800)value function: 0.237 -> 0.882Improved
replace K-O-L with L-JILK-O-L · Scenario 2 (p=20, n=800)value function: 0.276 -> 1.299Improved
replace Q-Linear with L-JILQ-Linear · Scenario 1 (p=20, n=800)value function: 0.829 -> 1.297Improved
replace L-O-L with L-JILL-O-L · Scenario 5 (p=20, n=800)value function: 7.81 -> 7.16Hurt
increase sample size from 50 to 800L-JIL · Scenario 1 (p=20)value function: 0.783 -> 1.297Improved
increase sample size from 200 to 800L-JIL · Scenario 1 (p=4)CI coverage probability (%): 89.80 -> 95.60Improved
increase sample size from 200 to 800L-JIL · Scenario 1 (p=4)integrated l2 loss of varying coefficient: 0.371 -> 0.111Improved
use m=n/6 instead of m=n/10 (ablation)L-JIL · Scenario 1 (p=20, n=800)value function: 1.297 -> 1.289No clear effect
use m=n/6 instead of m=n/10 (ablation)D-JIL · Scenario 1 (p=20, n=800)value function: 1.138 -> 1.127No clear effect
use m=n/6 instead of m=n/10 (ablation)D-JIL · Scenario 1 (p=20, n=800)computation time (minutes): 35.48 -> 87.56Hurt

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