Bounded Low Latency via Inverse Reinforcement Learning
Bibliographic record
Abstract
Accurate traffic prediction is essential for effective resource utilization and improving user experience quality in next generation wireless networks. Machine Learning (ML) techniques offer promising results for traditional scenarios; however, pre-sampling network traffic for training purposes often results in significant computing and memory requirements. Additionally, in many applications, such as wireless sensor networks (WSNs), the nodes’ energy constraints may limit the feasibility of network traffic sampling. Inverse Reinforcement Learning (IRL), which involves learning an agent’s objectives by observing its behavior, has gained significant attention in various fields, including autonomous driving, robotics, and aerial imagery-based navigation. In this paper, we propose the first application of IRL to network traffic flow prediction, used as an efficient tool for large-scale objective-aware traffic prediction purposes. We first model the traffic prediction problem using an IRL framework and then apply our proposed approach to a scheduling problem for packets with bounded latency requirements. Our simulation results demonstrate that IRL can provide better performance compared to well-known ML-based approaches while significantly reducing the amount of computation and memory required for real-time objective-oriented prediction scenarios. Therefore, this work presents a new direction for addressing network traffic prediction challenges by leveraging the benefits of IRL techniques. The proposed IRL-based approach offers a promising solution to reduce the computing and memory overheads associated with traditional ML-based approaches, leading to more efficient network traffic management.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".