English

Adaptive Data Exploitation in Deep Reinforcement Learning

Machine Learning 2025-01-23 v1 Artificial Intelligence

Abstract

We introduce ADEPT: Adaptive Data ExPloiTation, a simple yet powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL). Specifically, ADEPT adaptively manages the use of sampled data across different learning stages via multi-armed bandit (MAB) algorithms, optimizing data utilization while mitigating overfitting. Moreover, ADEPT can significantly reduce the computational overhead and accelerate a wide range of RL algorithms. We test ADEPT on benchmarks including Procgen, MiniGrid, and PyBullet. Extensive simulation demonstrates that ADEPT can achieve superior performance with remarkable computational efficiency, offering a practical solution to data-efficient RL. Our code is available at https://github.com/yuanmingqi/ADEPT.

Keywords

Cite

@article{arxiv.2501.12620,
  title  = {Adaptive Data Exploitation in Deep Reinforcement Learning},
  author = {Mingqi Yuan and Bo Li and Xin Jin and Wenjun Zeng},
  journal= {arXiv preprint arXiv:2501.12620},
  year   = {2025}
}

Comments

40 pages, 37 figures

R2 v1 2026-06-28T21:13:09.236Z