AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Stable Deep Reinforcement Learning via Isotropic Gaussian Representations

Ali Saheb Pasand, Johan Obando-Ceron, Aaron Courville, Pouya Bashivan, Pablo Samuel Castro

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent-space control and planning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SIGReg isotropic Gaussian regularization to PQNPQN · Full Atari (57 games)games improved / mean AUC improvement: 51 of 57 games improved; mean AUC improvement of 889% and median of 138%Improved
add SIGReg to PQN to keep embedding covariance spread over componentsPQN · Atari-10 PCA of embedding covarianceleading-component variance share: PQN: [0.4,0.2] -> [0.9,0.8] vs PQN+SIGReg: [0.3,0.2] -> [0.1,0.1]Improved
replace Gaussian target with Laplacian or Logistic isotropic target distributions (ablation)PQN + SIGReg · Atari-10AUC improvementHurt
use covariance whitening only (isotropy without Gaussian tails) instead of SIGReg (ablation)PQN · Atari-10AUC improvementHurt
enforce both symmetry and tail behavior rather than only one (ablation)PQN + SIGReg · Atari-10AUC improvementImproved
add SIGReg on top of baseline first-order optimizer to match Kronecker-factored optimizerPQN with RAdam · Atari-10performance gap to Kronecker-factored optimizerImproved
add SIGReg compared with VICReg, norm regularization, simplicial embeddings, weight orthogonalizationPQN · Atari-10average improvementImproved
add SIGReg to PPOPPO · Full AtariIQM human-normalized score and AUCImproved
add Kronecker-factored optimization or multi-skip residuals to PPOPPO · Full AtariperformanceHurt
add SIGReg to continuous control agentsIsaac Gym agents · Isaac Gym (5 seeds)training stability and varianceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy