Lune

ICML2026Top-tier venue

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

Abstract

Forecasting multivariate hidden Markov processes is challenging due to nonlinear and nonstationary observations, latent state transitions, and cross-sequence dependencies. While deep learning methods achieve strong predictive accuracy, they typically lack explicit state modeling, whereas Hidden Markov Models (HMMs) provide interpretable latent states but struggle with complex nonlinear emissions and scalability. To address these limitations, we propose DRL-STAF, a D eep R einforcement L earning based ST ate- A ware F orecasting framework that jointly predicts next-step observations and estimates the corresponding hidden states for complex multivariate hidden Markov processes. Specifically, DRL-STAF models complex nonlinear emissions using deep neural networks and estimates discrete hidden states using reinforcement learning, reducing the reliance on predefined transition structures and enabling flexible adaptation to diverse temporal dynamics. In particular, DRL-STAF mitigates the state-space explosion encountered by typical multivariate HMM-based methods. Extensive experiments demonstrate that DRL-STAF outperforms HMM variants, standalone deep learning models, and existing DL-HMM hybrids in most cases, while also providing reliable hidden-state estimates.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Spectral Temporal Graph Neural Network for Multivariate Time-series ForecastingDefu Cao, Yujing Wang, Juanyong Duan, Ce Zhang et al.NeurIPS 2020 · 841 citations
  2. Bayesian Model Selection, the Marginal Likelihood, and GeneralizationSanae Lotfi, Pavel Izmailov, Gregory W. Benton, Micah Goldblum et al.ICML 2022 · 83 citations
  3. Temporally Disentangled Representation Learning under Unknown NonstationarityXiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong et al.NeurIPS 2023 · 36 citations

Related papers

  1. Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series ForecastingNam Nguyen, Brian QuanzAAAI 2021 · 87 citations
  2. Deep Bayesian Filter for Bayes-Faithful Data AssimilationYuta Tarumi, Keisuke Fukuda, Shin-ichi MaedaICML 2025
  3. eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modelingMatthew Dowling, Yuan Zhao, Il Memming ParkNeurIPS 2024 · 17 citations
  4. Probabilistic Transformer For Time Series AnalysisBinh Tang, David S. MattesonNeurIPS 2021 · 150 citations
  5. Identifying latent state transitions in non-linear dynamical systemsÇaglar Hizli, Çagatay Yildiz, Matthias Bethge, S. T. John et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines