arXiv:2602.19373v2 Announce Type: replace-cross
Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian embeddings are provably advantageous. In particular, they induce stable tracking of time-varying targets for linear readouts, achieve maximal entropy under a fixed variance budget, and encourage a balanced use of all representational dimensions–all of which enable agents to be more adaptive and stable. Building on this insight, we propose the use of Sketched Isotropic Gaussian Regularization for shaping representations toward an isotropic Gaussian distribution during training. We demonstrate empirically, over a variety of domains, that this simple and computationally inexpensive method improves performance under non-stationarity while reducing representation collapse, neuron dormancy, and training instability.
Using an Adult-Designed Wearable for Pediatric Monitoring: Practical Tutorial and Application in School-Aged Children With Obesity
This tutorial presents a step-by-step guide on how to use an adult-oriented wearable (Fitbit) to collect and analyze activity and cardiovascular data in a pediatric