Adaptive Data Exploitation in Deep Reinforcement Learning
Yuan, Mingqi, Li, Bo, Jin, Xin, Zeng, Wenjun
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-21-2025
- Country:
- Asia > China (0.28)
- North America > United States (0.28)
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Energy (0.67)
- Leisure & Entertainment > Games (0.45)
- Technology: