# Decorrelated Double Q-learning

arXiv: https://arxiv.org/abs/2006.06956 · HTML: https://mlsanity.com/paper/2006.06956/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [On the Estimation Bias in Double Q-Learning](https://mlsanity.com/paper/2109.14419/) (2021)
- [Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning](https://mlsanity.com/paper/2111.07169/) (2021)
- [Deep Double Q-learning](https://mlsanity.com/paper/2507.00275/) (2025)

## Abstract (arXiv)

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.