AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks

Muthukumar Pandaram, Jakob Hollenstein, David Drexel, Samuele Tosatto, Antonio Rodriguez-Sanchez, Justus Piater

AAAI 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 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 ground-truth Jacobian MAE loss (ablation)MLP dynamics model · MLP world model on MuJoCo Playgroundnext-state prediction errorNo clear effect
add ground-truth Jacobian MSE loss (ablation)MLP dynamics model · MLP world model on MuJoCo Playgroundnext-state prediction errorNo clear effect
add ground-truth Jacobian losses (ablation)MLP dynamics model · MLP world model on MuJoCo Playgroundinduced Jacobian sparsityImproved
add sparsity-aware error (SAE) loss on expected-zero Jacobian entries (ablation)MLP dynamics model · MLP world model on MuJoCo Playgroundinduced sparsity and prediction errorImproved
add L1 penalty on predicted Jacobians (ablation)MLP dynamics model · MLP world model on MuJoCo Playgroundnext-state prediction accuracyHurt
reduce MLP depth from 6 to 2 layers (ablation)MLP dynamics model · MLP hyperparameter search 1mean test rank (lower better): 533.62 -> 245.32Improved
reduce dropout from 0.50 to 0.10 (ablation)MLP dynamics model · MLP hyperparameter search 1mean test rank (lower better): 563.64 -> 237.48Improved
use learning rate 0.001 instead of 0.01 (ablation)MLP dynamics model · MLP hyperparameter search 1mean test rank (lower better): 515.75 -> 338.43Improved
increase layer width from 32 to 512 (ablation)MLP dynamics model · MLP hyperparameter search 1mean test rank (lower better): 420.80 -> 396.23Improved
use ELU instead of leaky-ReLU (ablation)MLP dynamics model · MLP hyperparameter search 3mean test rank (lower better): 12.80 -> 8.05Improved
increase width from 512 to 1024 (ablation)MLP dynamics model · MLP hyperparameter search 2mean test rank (lower better): 19.75 -> 21.25No clear effect

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