Authors

Venue

Date

Share

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

Hojoon Lee

Dongyoon Hwang

Donghu Kim

Hyunseung Kim

Jun Jet Tai

Kaushik Subramanian

Peter R. Wurman

Jaegul Choo

Peter Stone

Takuma Seno

ICLR-25

2025

Abstract

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.

Related Publications

Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning

ICML, 2025
Siddhant Agarwal*, Harshit Sikchi, Peter Stone, Amy Zhang*

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as ``zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While rec…

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

ICML, 2025
Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo

Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data easily leads to overfitting and unstab…

A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7

RA-L, 2025
Hojoon Lee, Takuma Seno, Jun Jet Tai, Kaushik Subramanian, Kenta Kawamoto, Peter Stone, Peter R. Wurman

Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require instrumentation external to a car, such as precise localization of agents and opponents, limiting …

  • HOME
  • Publications
  • SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.