# Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization

arXiv: https://arxiv.org/abs/2502.07523 · HTML: https://mlsanity.com/paper/2502.07523/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 11 Feb 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, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research](https://mlsanity.com/paper/1802.09464/) (2018)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Learning Continuous Control Policies by Stochastic Value Gradients](https://mlsanity.com/paper/1510.09142/) (2015)
- [Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning](https://mlsanity.com/paper/1803.00101/) (2018)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [L2 Regularization versus Batch and Weight Normalization](https://mlsanity.com/paper/1706.05350/) (2017)
- [When to use parametric models in reinforcement learning?](https://mlsanity.com/paper/1906.05243/) (2019)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control](https://mlsanity.com/paper/2405.16158/) (2024)
- [CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity](https://mlsanity.com/paper/1902.05605/) (2019)
- [Normalization Techniques in Training DNNs: Methodology, Analysis and Application](https://mlsanity.com/paper/2009.12836/) (2020)
- [Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units](https://mlsanity.com/paper/1603.05201/) (2016)
- [MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control](https://mlsanity.com/paper/2205.13600/) (2022)
- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024)
- [Normalization and effective learning rates in reinforcement learning](https://mlsanity.com/paper/2407.01800/) (2024)
- [PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning](https://mlsanity.com/paper/2306.10711/) (2023)
- [Efficient Deep Reinforcement Learning Requires Regulating Overfitting](https://mlsanity.com/paper/2304.10466/) (2023)

## Built on by (most cited first, 19 of 19)

- [Hyperspherical Normalization for Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.15280/) (2025)
- [XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning](https://mlsanity.com/paper/2509.25174/) (2025)
- [Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion](https://mlsanity.com/paper/2503.08375/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning](https://mlsanity.com/paper/2506.04398/) (2025)
- [Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning](https://mlsanity.com/paper/2510.02590/) (2025)
- [Temporal Difference Learning with Constrained Initial Representations](https://mlsanity.com/paper/2602.11800/) (2026)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies](https://mlsanity.com/paper/2605.10734/) (2026)
- [Debiased Model-based Representations for Sample-efficient Continuous Control](https://mlsanity.com/paper/2605.11711/) (2026)
- [Behavior-Consistent Deep Reinforcement Learning](https://mlsanity.com/paper/2605.21214/) (2026)
- [An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms](https://mlsanity.com/paper/2509.23750/) (2025)
- [Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2604.18978/) (2026)
- [Extending Differential Temporal Difference Methods for Episodic Problems](https://mlsanity.com/paper/2605.04368/) (2026)
- [Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards](https://mlsanity.com/paper/2606.02194/) (2026)
- [Momba: Network Modernization Improves Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2608.07180/) (2026)
- [V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control](https://mlsanity.com/paper/2608.07870/) (2026)
- [On BatchNorm Forward Modes in Value-Based Reinforcement Learning](https://mlsanity.com/paper/2609.06421/) (2026)
- [Rank Collapse Is Recoverable, Growing |Q| Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic](https://mlsanity.com/paper/2609.32819/) (2026)

## Abstract (arXiv)

Reinforcement learning has achieved significant milestones, but sample efficiency remains a bottleneck for real-world applications. Recently, CrossQ has demonstrated state-of-the-art sample efficiency with a low update-to-data (UTD) ratio of 1. In this work, we explore CrossQ's scaling behavior with higher UTD ratios. We identify challenges in the training dynamics, which are emphasized by higher UTD ratios. To address these, we integrate weight normalization into the CrossQ framework, a solution that stabilizes training, has been shown to prevent potential loss of plasticity and keeps the effective learning rate constant. Our proposed approach reliably scales with increasing UTD ratios, achieving competitive performance across 25 challenging continuous control tasks on the DeepMind Control Suite and Myosuite benchmarks, notably the complex dog and humanoid environments. This work eliminates the need for drastic interventions, such as network resets, and offers a simple yet robust pathway for improving sample efficiency and scalability in model-free reinforcement learning.