Adaptive Data Exploitation in Deep Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Mingqi, Li, Bo, Jin, Xin, Zeng, Wenjun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909463761387520
author Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
author_facet Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Data Exploitation in Deep Reinforcement Learning
Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
Machine Learning
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.
title Adaptive Data Exploitation in Deep Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.12620