AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

DRL-STAF: A Deep Reinforcement Learning Framework for State-Aware Forecasting of Complex Multivariate Hidden Markov Processes

Manrui Jiang, Jingru Huang, Yong Chen, Chen Zhang

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 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 hidden-state modeling (DRL-S1 over DL-F) (ablation)DL-F forecaster · Simulated 3 variablesMAE: 0.2599 -> 0.0956Improved
add hidden-state modeling (DRL-S1 over DL-F) (ablation)DL-F forecaster · Simulated 10 variablesMAE: 0.3646 -> 0.1129Improved
add hidden-state modeling (DRL-S1 over DL-F) (ablation)DL-F forecaster · ExchangeMAE: 3.5285 -> 1.8412Improved
add hidden-state modeling (DRL-S1 over DL-F) (ablation)DL-F forecaster · TrafficMAE: 1.8387 -> 1.5686Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · Simulated 3 variablesMAE: 0.0956 -> 0.0889Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · Simulated 10 variablesMAE: 0.1129 -> 0.1090Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · ExchangeMAE: 1.8412 -> 1.7249Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · TrafficMAE: 1.5686 -> 1.5193Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · Simulated 3 variablesaccuracy: 97.53% -> 98.17%Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · SMachineaccuracy: 85.80% -> 81.73%Hurt
add second-stage cross-variable interaction training (ablation)DRL-S1 · SMachineF1: 72.85% -> 77.50%Improved
add second-stage cross-variable interaction training (ablation)DRL-S1 · Simulated 10 variablesrecall: 93.23% -> 91.89%Hurt

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