# Adapting Double Q-Learning for Continuous Reinforcement Learning

arXiv: https://arxiv.org/abs/2309.14471 · HTML: https://mlsanity.com/paper/2309.14471/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 5 of 5)

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics](https://mlsanity.com/paper/2005.04269/) (2020)
- [Maxmin Q-learning: Controlling the Estimation Bias of Q-learning](https://mlsanity.com/paper/2002.06487/) (2020)

## Built on by (most cited first, 1 of 1)

- [Context-Aware Information Transfer via Digital Semantic Communication in UAV-Based Networks](https://mlsanity.com/paper/2601.01430/) (2026)

## Abstract (arXiv)

Majority of off-policy reinforcement learning algorithms use overestimation bias control techniques. Most of these techniques rooted in heuristics, primarily addressing the consequences of overestimation rather than its fundamental origins. In this work we present a novel approach to the bias correction, similar in spirit to Double Q-Learning. We propose using a policy in form of a mixture with two components. Each policy component is maximized and assessed by separate networks, which removes any basis for the overestimation bias. Our approach shows promising near-SOTA results on a small set of MuJoCo environments.