Imitation Learning Backoff: Reinforcement Learning-Based Channel Access for Guaranteeing Fairness (Student Abstract)

AAAI 2025 pp. 29401-29403

doi:10.1609/AAAI.V39I28.35266 /aaai/2025/lee2025aaai-imitation/

Abstract

This paper addresses contention window optimization for multi-access scenarios. Our investigation into state-of-the-art models revealed that a limited number of nodes dominate the communication channels. Such monopolization issues are critical in networks as they can lead to significant disruptions. To mitigate this monopolization problem, we propose an imitation learning-based backoff mechanism. The proposed model is a reinforcement learning-based contention window optimization method. It imitates the expert's policy to ensure fair policy convergence for the agent and includes opportunities for weight adjustment to boost performance. The proposed model shows a fairness improvement of approximately 20% to 41% across various scenarios.

AAAI Semantic Scholar

Cite

Text

Lee and Jo. "Imitation Learning Backoff: Reinforcement Learning-Based Channel Access for Guaranteeing Fairness (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35266

Markdown

[Lee and Jo. "Imitation Learning Backoff: Reinforcement Learning-Based Channel Access for Guaranteeing Fairness (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/lee2025aaai-imitation/) doi:10.1609/AAAI.V39I28.35266

BibTeX

@inproceedings{lee2025aaai-imitation,
  title     = {{Imitation Learning Backoff: Reinforcement Learning-Based Channel Access for Guaranteeing Fairness (Student Abstract)}},
  author    = {Lee, Taegyeom and Jo, Ohyun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {29401-29403},
  doi       = {10.1609/AAAI.V39I28.35266},
  url       = {https://mlanthology.org/aaai/2025/lee2025aaai-imitation/}
}