AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical Systems

Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi

NeurIPS 2018 · Probabilistic and scientific modeling › Dynamical systems · approach: State-space inference for stochastic systems

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 path-integral refinement (ablation)APIAE inference · Pendulumlower bound: -9.974 -> -9.927Improved
Add path-integral refinement (ablation)APIAE inference · Mocaplower bound: -6.683 -> -6.680Improved
Add resampling during training (ablation)APIAE · Pendulumprediction: -1.845 -> -1.985Hurt
Add resampling during training (ablation)APIAE · Pendulumlower bound: -9.927 -> -9.866Improved
Increase sample count from L=4 to L=64 (ablation)APIAE without resampling · Pendulumlower bound: -9.9724 -> -9.8552Improved
Increase sample count from L=4 to L=64 (ablation)APIAE without resampling · Mocaplower bound: -6.689 -> -6.629Improved
Increase adaptations from R=4 to R=8 (ablation)APIAE without resampling · Pendulumlower bound: -9.927 -> -9.929No clear effect
Increase adaptations from R=4 to R=8 (ablation)APIAE without resampling · Mocaplower bound: -6.680 -> -6.669Improved
Use path-integral refinement rather than no adaptationAPIAE · Pendulumreconstruction: -1.665 -> -1.653Improved
Use path-integral refinement rather than no adaptationAPIAE · Pendulumprediction: -1.860 -> -1.845Improved
Use path-integral refinement rather than no adaptationAPIAE · Mocaplower bound: -6.683 -> -6.680Improved
Use path-integral refinement rather than no adaptationAPIAE · Mocapreconstruction: -1.174 -> -1.171Improved

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