English

rQdia: Regularizing Q-Value Distributions With Image Augmentation

Machine Learning 2025-06-27 v1 Artificial Intelligence

Abstract

rQdia regularizes Q-value distributions with augmented images in pixel-based deep reinforcement learning. With a simple auxiliary loss, that equalizes these distributions via MSE, rQdia boosts DrQ and SAC on 9/12 and 10/12 tasks respectively in the MuJoCo Continuous Control Suite from pixels, and Data-Efficient Rainbow on 18/26 Atari Arcade environments. Gains are measured in both sample efficiency and longer-term training. Moreover, the addition of rQdia finally propels model-free continuous control from pixels over the state encoding baseline.

Cite

@article{arxiv.2506.21367,
  title  = {rQdia: Regularizing Q-Value Distributions With Image Augmentation},
  author = {Sam Lerman and Jing Bi},
  journal= {arXiv preprint arXiv:2506.21367},
  year   = {2025}
}
R2 v1 2026-07-01T03:34:42.272Z