# SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2410.09754 · HTML: https://mlsanity.com/paper/2410.09754/

## Key facts

- Cited by 76 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 59 of its 68 references that are in the map.
- First posted on arXiv 13 Oct 2024.

## 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 59)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [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)
- [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)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss](https://mlsanity.com/paper/2002.04486/) (2020)
- [Implicit Bias of Gradient Descent on Linear Convolutional Networks](https://mlsanity.com/paper/1806.00468/) (2018)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)

## Built on by (most cited first, 30 of 76)

- [Flow Q-Learning](https://mlsanity.com/paper/2502.02538/) (2025)
- [Horizon Reduction Makes RL Scalable](https://mlsanity.com/paper/2506.04168/) (2025)
- [1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities](https://mlsanity.com/paper/2503.14858/) (2025)
- [FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control](https://mlsanity.com/paper/2505.22642/) (2025)
- [Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners](https://mlsanity.com/paper/2505.23150/) (2025)
- [Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning](https://mlsanity.com/paper/2506.15544/) (2025)
- [floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL](https://mlsanity.com/paper/2509.06863/) (2025)
- [Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization](https://mlsanity.com/paper/2502.07523/) (2025)
- [XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning](https://mlsanity.com/paper/2509.25174/) (2025)
- [Learning Sim-to-Real Humanoid Locomotion in 15 Minutes](https://mlsanity.com/paper/2512.01996/) (2025)
- [Value-Based Deep RL Scales Predictably](https://mlsanity.com/paper/2502.04327/) (2025)
- [Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning](https://mlsanity.com/paper/2505.24061/) (2025)
- [Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents](https://mlsanity.com/paper/2510.13704/) (2025)
- [Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning](https://mlsanity.com/paper/2506.17204/) (2025)
- [Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning](https://mlsanity.com/paper/2510.01656/) (2025)
- [A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control](https://mlsanity.com/paper/2507.02712/) (2025)
- [Hadamax Encoding: Elevating Performance in Model-Free Atari](https://mlsanity.com/paper/2505.15345/) (2025)
- [Relative Entropy Pathwise Policy Optimization](https://mlsanity.com/paper/2507.11019/) (2025)
- [FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff](https://mlsanity.com/paper/2602.08040/) (2026)
- [Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning](https://mlsanity.com/paper/2503.05546/) (2025)
- [Compute-Optimal Scaling for Value-Based Deep RL](https://mlsanity.com/paper/2508.14881/) (2025)
- [Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control](https://mlsanity.com/paper/2509.01765/) (2025)
- [Stable Deep Reinforcement Learning via Isotropic Gaussian Representations](https://mlsanity.com/paper/2602.19373/) (2026)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [Evolutionary Policy Optimization](https://mlsanity.com/paper/2503.19037/) (2025)
- [Stagewise Reinforcement Learning and the Geometry of the Regret Landscape](https://mlsanity.com/paper/2601.07524/) (2026)
- [What Makes Value Learning Efficient in Residual Reinforcement Learning?](https://mlsanity.com/paper/2602.10539/) (2026)
- [Off-policy Reinforcement Learning with Model-based Exploration Augmentation](https://mlsanity.com/paper/2510.25529/) (2025)
- [Understanding and Improving Hyperbolic Deep Reinforcement Learning](https://mlsanity.com/paper/2512.14202/) (2025)
- [Spectral Representation-based Reinforcement Learning](https://mlsanity.com/paper/2512.15036/) (2025)

## Abstract (arXiv)

Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating components that induce a simplicity bias, guiding models toward simple and generalizable solutions. However, in deep RL, designing and scaling up networks have been less explored. Motivated by this opportunity, we present SimBa, an architecture designed to scale up parameters in deep RL by injecting a simplicity bias. SimBa consists of three components: (i) an observation normalization layer that standardizes inputs with running statistics, (ii) a residual feedforward block to provide a linear pathway from the input to output, and (iii) a layer normalization to control feature magnitudes. By scaling up parameters with SimBa, the sample efficiency of various deep RL algorithms-including off-policy, on-policy, and unsupervised methods-is consistently improved. Moreover, solely by integrating SimBa architecture into SAC, it matches or surpasses state-of-the-art deep RL methods with high computational efficiency across DMC, MyoSuite, and HumanoidBench. These results demonstrate SimBa's broad applicability and effectiveness across diverse RL algorithms and environments.