mlsanityData to 14 Oct 2026

Classification with Costly Features using Deep Reinforcement Learning

arXiv 1711.07364 ↗First posted 20 Nov 2017cs.AI cs.LG stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost. We revisit a former approach that has framed the problem as a sequential decision-making problem and solved it by Q-learning with a linear approximation, where individual actions are either requests for feature values or terminate the episode by providing a classification decision. On a set of eight problems, we demonstrate that by replacing the linear approximation with neural networks the approach becomes comparable to the state-of-the-art algorithms developed specifically for this problem. The approach is flexible, as it can be improved with any new reinforcement learning enhancement, it allows inclusion of pre-trained high-performance classifier, and unlike prior art, its performance is robust across all evaluated datasets.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 9; 2024: 2; 2025: 7; 2026: 9.

34 papers.

Sort:

By area:

  1. 2023Learning to Maximize Mutual Information for Dynamic Feature Selectioncited by 56
  2. 2023Deep Reinforcement Learning for Cost-Effective Medical Diagnosiscited by 21
  3. 2023Estimating Conditional Mutual Information for Dynamic Feature Selectioncited by 21
  4. 2025A Survey on Active Feature Acquisition Strategiescited by 17
  5. 2022Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Taskcited by 13
  6. 2023Clairvoyance: A Pipeline Toolkit for Medical Time Seriescited by 12
  7. 2025Stochastic Encodings for Active Feature Acquisitioncited by 9
  8. 2025DRMD: Deep Reinforcement Learning for Malware Detection under Concept Driftcited by 7
  9. 2022Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learningcited by 5
  10. 2025Learning-To-Measure: In-Context Active Feature Acquisitioncited by 5
  11. 2021Costly Features Classification using Monte Carlo Tree Searchcited by 4
  12. 2021Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networkscited by 3
22 more
  1. 2023RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithmcited by 3
  2. 2024Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosuscited by 3
  3. 2023Learning Computational Efficient Bots with Costly Featurescited by 2
  4. 2023Generator Assisted Mixture of Experts For Feature Acquisition in Batchcited by 2
  5. 2021Dynamic Instance-Wise Classification in Correlated Feature Spacescited by 1
  6. 2022UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classificationcited by 1
  7. 2023Fast Classification with Sequential Feature Selection in Test Phasecited by 1
  8. 2025Dynamic Feature Selection from Variable Feature Sets Using Features of Featurescited by 1
  9. 2025Model-Agnostic Dynamic Feature Selection with Uncertainty Quantificationcited by 1
  10. 2026When Should Humans Step In? Optimal Human Dispatching in AI-Assisted Decisionscited by 1
  11. 2022Scalable Online Disease Diagnosis via Multi-Model-Fused Actor-Critic Reinforcement Learningcited by 0
  12. 2023Extracting Diagnosis Pathways from Electronic Health Records Using Deep Reinforcement Learningcited by 0
  13. 2024EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networkscited by 0
  14. 2025AutoNFS: Automatic Neural Feature Selectioncited by 0
  15. 2026DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experimentscited by 0
  16. 2026Hypernetworks for Dynamic Feature Selectioncited by 0
  17. 2026Zero-Shot Active Feature Acquisition via LLM-Elicitationcited by 0
  18. 2026Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocationcited by 0
  19. 2026Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attributioncited by 0
  20. 2026Active Feature Acquisition With Incomplete Training Datacited by 0
  21. 2026A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferralcited by 0
  22. 2026Beyond Second-Order Information: Paid Logistic Regression with Noisy Featurescited by 0