Designing a double deep reinforcement learning selection tool for resilient demand prediction

• URL: http://arxiv.org/abs/2605.04068v1
• Date: Sun, 12 Apr 2026 18:52:32 GMT
• Title: Designing a double deep reinforcement learning selection tool for resilient demand prediction
• Abstract summary: This research aims to enhance automatic forecasting model selection.<n>It acts as a double deep reinforcement learning agent, selecting automatically a forecasting model from the forecasting committee.<n>A novel early-stopping approach based on average reward convergence has been introduced to expedite training time.
• Score: 0.6766416093990317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The use of artificial intelligence in supply chain forecasting has attracted many scientific studies for several decades. However, the process of selecting an appropriate forecasting solution becomes a daunting task. This complexity arises due to the distinct features inherent to each dataset. Research to tackle this issue has been performed since the eighties but recent development of demand forecasting has opened new perspectives. This research aims to enhance automatic forecasting model selection by proposing a novel architecture that acts as a double deep reinforcement learning agent, selecting automatically a forecasting model from the forecasting committee at the time of prediction. Moreover, a novel early-stopping approach based on average reward convergence has been introduced to expedite training time. To evaluate the model's performance, an empirical study was conducted utilizing grocery sales datasets and snack demands datasets. The experimental results demonstrate the robustness of the proposed approach when compared to state-of-the-art methods.

Related papers

• Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting [26.28141834580785]
  Foundation models have emerged as a promising paradigm for zero-shot time series forecasting.<n>They are pre-trained on vast and diverse collections of time series, learning generalizable representations that support both point and probabilistic forecasting.<n>This approach alleviates the need for dataset-specific model design and manual tuning, offering a unified solution across forecasting problems.
  arXiv  Detail & Related papers  (2026-07-25T10:55:06Z)
• Learning to Predict Future-Aligned Research Proposals with Language Models [59.79457676644722]
  We build a time-consistent dataset of 17,771 papers from targets and their pre-cutoff citations.<n>To train models, we build a time-consistent dataset of 17,771 papers from targets and their pre-cutoff citations.<n>Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines.
  arXiv  Detail & Related papers  (2026-03-28T05:41:15Z)
• Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting [22.256909587855905]
  We propose Cast-R1, a learned time series forecasting framework that reformulates forecasting as a sequential decision-making problem.<n>Cast-R1 introduces a memory-based state management mechanism that maintains decision-relevant information across interaction steps.<n>Building on this formulation, forecasting is carried out through a tool-augmented agentic workflow.
  arXiv  Detail & Related papers  (2026-02-14T14:27:08Z)
• Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting [49.05788441962762]
  We argue for agentic time series forecasting (ATSF), which reframes forecasting as an agentic process composed of perception, planning, action, reflection, and memory.<n>We outline three representative implementation paradigms -- workflow-based design, agentic reinforcement learning, and a hybrid agentic workflow paradigm -- and discuss the opportunities and challenges that arise when shifting from model-centric prediction to agentic forecasting.
  arXiv  Detail & Related papers  (2026-02-02T08:01:11Z)
• Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting [63.8116386935854]
  We demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized trainings.<n>We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector.<n>We find that our framework design is robust to the choice of probabilistic estimators, seamlessly supporting interpolants, diffusion models, and CRPS-based ensemble training.
  arXiv  Detail & Related papers  (2026-01-26T03:52:16Z)
• Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models [45.523937630646394]
  We propose SFP Forecasting as Planning (SFP), a new paradigm in Model Based Reinforcement Learning.<n>SFP constructs a novel World Model to simulate diverse high-temporal future states, enabling an "imagination-based" environmental simulation.
  arXiv  Detail & Related papers  (2025-10-05T03:57:38Z)
• Risk Analysis and Design Against Adversarial Actions [1.9573380763700716]
  We propose a versatile, well-principled framework to evaluate the model's robustness against attacks of diverse types and intensities.<n>Results enable an assessment of the model vulnerability without requiring additional test data and operate in a distribution-free setup.
  arXiv  Detail & Related papers  (2025-05-02T09:16:44Z)
• AALF: Almost Always Linear Forecasting [3.336367986372977]
  We argue that simple models are good enough most of the time, and that forecasting performance could be improved by choosing a Deep Learning method only for few, important predictions.<n>An empirical study on various real-world datasets shows that our selection methodology performs comparable to state-of-the-art online model selections methods in most cases.<n>We find that almost always choosing a simple autoregressive linear model for forecasting results in competitive performance.
  arXiv  Detail & Related papers  (2024-09-16T10:13:09Z)
• ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting [74.00765474305288]
  We present a pilot study on using reinforcement learning (RL) for time series data augmentation.<n>Our method, ReAugment, tackles three critical questions: which parts of the training set should be augmented, how the augmentation should be performed, and what advantages RL brings to the process.
  arXiv  Detail & Related papers  (2024-09-10T07:34:19Z)
• F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data [65.6499834212641]
  We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm. By considering domain similarities through task-specific metadata, our model improved generalization, where the excess risk decreases as the number of training tasks increases. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
  arXiv  Detail & Related papers  (2024-06-23T21:28:50Z)
• An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation [91.62129090006745]
  This paper studies the distribution shift problem from the perspective of pre-training and data augmentation. We provide the first comprehensive empirical study focusing on pre-training and data augmentation.
  arXiv  Detail & Related papers  (2022-05-25T13:04:53Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• Profit-oriented sales forecasting: a comparison of forecasting techniques from a business perspective [3.613072342189595]
  This paper compares a large array of techniques for 35 times series that consist of both industry data from the Coca-Cola Company and publicly available datasets. It introduces a novel and completely automated profit-driven approach that takes into account the expected profit that a technique can create during both the model building and evaluation process.
  arXiv  Detail & Related papers  (2020-02-03T14:50:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.