# An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms

arXiv: https://arxiv.org/abs/2509.23750 · HTML: https://mlsanity.com/paper/2509.23750/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 23 of 23)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Soft Actor-Critic for Discrete Action Settings](https://mlsanity.com/paper/1910.07207/) (2019)
- [Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models](https://mlsanity.com/paper/1702.03275/) (2017)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity](https://mlsanity.com/paper/1902.05605/) (2019)
- [Iterative Normalization: Beyond Standardization towards Efficient Whitening](https://mlsanity.com/paper/1904.03441/) (2019)
- [Bayesian Uncertainty Estimation for Batch Normalized Deep Networks](https://mlsanity.com/paper/1802.06455/) (2018)
- [Heterogeneous-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.09870/) (2023)
- [Normalization and effective learning rates in reinforcement learning](https://mlsanity.com/paper/2407.01800/) (2024)
- [Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization](https://mlsanity.com/paper/2502.07523/) (2025)
- [An Investigation into the Stochasticity of Batch Whitening](https://mlsanity.com/paper/2003.12327/) (2020)
- [Delving into the Estimation Shift of Batch Normalization in a Network](https://mlsanity.com/paper/2203.10778/) (2022)
- [Stochastic Normalizations as Bayesian Learning](https://mlsanity.com/paper/1811.00639/) (2018)

## Abstract (arXiv)

Batch Normalization (BN) has played a pivotal role in the success of deep learning by improving training stability, mitigating overfitting, and enabling more effective optimization. However, its adoption in deep reinforcement learning (DRL) has been limited due to the inherent non-i.i.d. nature of data and the dynamically shifting distributions induced by the agent's learning process. In this paper, we argue that, despite these challenges, BN retains unique advantages in DRL settings, particularly through its stochasticity and its ability to ease training. When applied appropriately, BN can adapt to evolving data distributions and enhance both convergence speed and final performance. To this end, we conduct a comprehensive empirical study on the use of BN in off-policy actor-critic algorithms, systematically analyzing how different training and evaluation modes impact performance. We further identify failure modes that lead to instability or divergence, analyze their underlying causes, and propose the Mode-Aware Batch Normalization (MA-BN) method with practical actionable recommendations for robust BN integration in DRL pipelines. We also empirically validate that, in RL settings, MA-BN accelerates and stabilizes training, broadens the effective learning rate range, enhances exploration, and reduces overall optimization difficulty. Our code is available at: https://github.com/monster476/ma-bn.git.