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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add path-integral refinement (ablation) | APIAE inference · Pendulum | lower bound: -9.974 -> -9.927 | Improved |
| Add path-integral refinement (ablation) | APIAE inference · Mocap | lower bound: -6.683 -> -6.680 | Improved |
| Add resampling during training (ablation) | APIAE · Pendulum | prediction: -1.845 -> -1.985 | Hurt |
| Add resampling during training (ablation) | APIAE · Pendulum | lower bound: -9.927 -> -9.866 | Improved |
| Increase sample count from L=4 to L=64 (ablation) | APIAE without resampling · Pendulum | lower bound: -9.9724 -> -9.8552 | Improved |
| Increase sample count from L=4 to L=64 (ablation) | APIAE without resampling · Mocap | lower bound: -6.689 -> -6.629 | Improved |
| Increase adaptations from R=4 to R=8 (ablation) | APIAE without resampling · Pendulum | lower bound: -9.927 -> -9.929 | No clear effect |
| Increase adaptations from R=4 to R=8 (ablation) | APIAE without resampling · Mocap | lower bound: -6.680 -> -6.669 | Improved |
| Use path-integral refinement rather than no adaptation | APIAE · Pendulum | reconstruction: -1.665 -> -1.653 | Improved |
| Use path-integral refinement rather than no adaptation | APIAE · Pendulum | prediction: -1.860 -> -1.845 | Improved |
| Use path-integral refinement rather than no adaptation | APIAE · Mocap | lower bound: -6.683 -> -6.680 | Improved |
| Use path-integral refinement rather than no adaptation | APIAE · Mocap | reconstruction: -1.174 -> -1.171 | Improved |
Closest papers by meaning
- Identifying latent state transitions in non-linear dynamical systems (ICLR 2025 · similarity 0.87)
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.87)
- Environment Inference for Learning Generalizable Dynamical System (NeurIPS 2025 · similarity 0.86)
- Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems (NeurIPS 2025 · similarity 0.85)
- Learning Hybrid Dynamics Models with Simulator-Informed Latent States (AAAI 2024 · similarity 0.85)
- Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images (ICLR 2025 · similarity 0.85)
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.
