mlsanityData to 14 Oct 2026

Policy Gradient Algorithms for Age-of-Information Cost Minimization

arXiv 2512.11990 ↗First posted 12 Dec 2025cs.NI cs.IT cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Recent developments in cyber-physical systems have increased the importance of maximizing the freshness of the information about the physical environment. However, optimizing the access policies of Internet of Things devices to maximize the data freshness, measured as a function of the Age-of-Information (AoI) metric, is a challenging task. This work introduces two algorithms to optimize the information update process in cyber-physical systems operating under the generate-at-will model, by finding an online policy without knowing the characteristics of the transmission delay or the age cost function. The optimization seeks to minimize the time-average cost, which integrates the AoI at the receiver and the data transmission cost, making the approach suitable for a broad range of scenarios. Both algorithms employ policy gradient methods within the framework of model-free reinforcement learning (RL) and are specifically designed to handle continuous state and action spaces. Each algorithm minimizes the cost using a distinct strategy for deciding when to send an information update. Moreover, we demonstrate that it is feasible to apply the two strategies simultaneously, leading to an additional reduction in cost. The results demonstrate that the proposed algorithms exhibit good convergence properties and achieve a time-average cost within 3% of the optimal value, when the latter is computable. A comparison with other state-of-the-art methods shows that the proposed algorithms outperform them in one or more of the following aspects: being applicable to a broader range of scenarios, achieving a lower time-average cost, and requiring a computational cost at least one order of magnitude lower.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 37 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

10 of 37 references.

References · 10

  1. 2020Age of Information: An Introduction and Surveycited by 70
  2. 2018Sampling for Data Freshness Optimization: Non-linear Age Functionscited by 10
  3. 2019A Reinforcement Learning Framework for Optimizing Age-of-Information in RF-powered Communication Systemscited by 10
  4. 2020AoI Minimization in Status Update Control with Energy Harvesting Sensorscited by 10
  5. 2021A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQcited by 9
  6. 2019Timely Cloud Computing: Preemption and Waitingcited by 3
  7. 2017The Age of Information in Multihop Networkscited by 2
  8. 2022Average Age of Information Penalty of Short-Packet Communications with Packet Managementcited by 2
  9. 2021Non-Linear Age of Information: An Energy Efficient Receiver-Centric Approachcited by 1
  10. 2024When to Preempt in a Status Update System?cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning
  2. 2025Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks
  3. 2026Diffusion Model-based Reinforcement Learning for Version Age of Information Scheduling: Average and Tail-Risk-Sensitive Control
  4. 2026Transformer Actor-Critic for Efficient Freshness-Aware Resource Allocation
  5. 2025Age-of-information minimization under energy harvesting and non-stationary environment
  6. 2026Joint Freshness and Age-Dispersion Control over Finite-State Markov Wireless Channels ↗
  7. 2024Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
  8. 2025Age of Information Minimization in UAV-Enabled Integrated Sensing and Communication Systems