Infant Spontaneous Movement Noise Improves Exploration in Deep RL

[Submitted on 15 Jun 2026 (v1), last revised 16 Jun 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract: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 this https URL.

Submission history

From: Francisco M. López [view email]
[v1] Mon, 15 Jun 2026 11:35:06 UTC (1,672 KB)
[v2] Tue, 16 Jun 2026 02:50:13 UTC (1,672 KB)