English

ADDQ: Adaptive Distributional Double Q-Learning

Machine Learning 2025-06-26 v1 Optimization and Control

Abstract

Bias problems in the estimation of QQ-values are a well-known obstacle that slows down convergence of QQ-learning and actor-critic methods. One of the reasons of the success of modern RL algorithms is partially a direct or indirect overestimation reduction mechanism. We propose an easy to implement method built on top of distributional reinforcement learning (DRL) algorithms to deal with the overestimation in a locally adaptive way. Our framework is simple to implement, existing distributional algorithms can be improved with a few lines of code. We provide theoretical evidence and use double QQ-learning to show how to include locally adaptive overestimation control in existing algorithms. Experiments are provided for tabular, Atari, and MuJoCo environments.

Keywords

Cite

@article{arxiv.2506.19478,
  title  = {ADDQ: Adaptive Distributional Double Q-Learning},
  author = {Leif Döring and Benedikt Wille and Maximilian Birr and Mihail Bîrsan and Martin Slowik},
  journal= {arXiv preprint arXiv:2506.19478},
  year   = {2025}
}
R2 v1 2026-07-01T03:31:21.268Z