Infant Spontaneous Movement Noise Improves Exploration in Deep RL
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise can improve exploration efficiency by producing smooth trajectories with better coverage of the state space. We inquire whether action noise inspired by infant spontaneous movements can also improve exploration in deep RL. We find that the power spectral densities of babies' end-effector velocities follow a colored noise process where the spectral exponent increases with age. Inspired by this developmental pattern, we introduce a mechanism that progressively increases the temporal auto-correlation of exploration noise during RL training, matching the infant statistics. Experiments across several RL environments show that infant-inspired noise produces structured exploratory behavior and can improve learning efficiency compared to conventional exploration strategies. These findings suggest that human motor and cognitive development can provide useful guidance for designing learning mechanisms in artificial agents. Our code is available at https://github.com/trieschlab/baby-noise-rl.
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 10 of its 30 references that are in the map. First posted on arXiv 15 Jun 2026.
Builds on
10 of 30 references.
References · 10
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
- 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 95
- 2022Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performancecited by 22
- 2022Time to augment self-supervised visual representation learningcited by 15
- 2023Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Samplingcited by 8
- 2023MIMo: A Multi-Modal Infant Model for Studying Cognitive Developmentcited by 2
- 2025MIMo grows! Simulating body and sensory development in a multimodal infant modelcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Evaluating Robots Like Human Infants: A Case Study of Learned Bipedal Locomotion ↗
- 2022Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
- 2026StructRL: Structured Action-Space Exploration for Flow-Based VLAs
- 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning
- 2018Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation
- 2025From Kicking to Causality: Simulating Infant Agency Detection with a Robust Intrinsic Reward
- 2026Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy
- 2025Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration