English

Decorrelated Double Q-learning

Machine Learning 2020-06-15 v1 Artificial Intelligence

Abstract

Q-learning with value function approximation may have the poor performance because of overestimation bias and imprecise estimate. Specifically, overestimation bias is from the maximum operator over noise estimate, which is exaggerated using the estimate of a subsequent state. Inspired by the recent advance of deep reinforcement learning and Double Q-learning, we introduce the decorrelated double Q-learning (D2Q). Specifically, we introduce the decorrelated regularization item to reduce the correlation between value function approximators, which can lead to less biased estimation and low variance. The experimental results on a suite of MuJoCo continuous control tasks demonstrate that our decorrelated double Q-learning can effectively improve the performance.

Keywords

Cite

@article{arxiv.2006.06956,
  title  = {Decorrelated Double Q-learning},
  author = {Gang Chen},
  journal= {arXiv preprint arXiv:2006.06956},
  year   = {2020}
}

Comments

8 pages, 5 figures

R2 v1 2026-06-23T16:15:52.516Z