Research map / Probabilistic and scientific modeling / Dynamical systems
End-to-End Differentiable Physics for Learning and Control
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use analytic LCP gradients instead of finite differences | differentiable physics engine · chain mass inference | run time | Helped |
| embed differentiable physics engine in autoencoder instead of MLP dynamics | visual prediction autoencoder · billiard ball video prediction | validation MSE | Helped |
| add unlabeled data trained through physics engine with decoder loss (ablation) | physics autoencoder · billiard ball video prediction | sample efficiency | Helped |
| use physics-engine model instead of MLP for iLQR control | iLQR controller · Cartpole | reward | Helped |
| physics-engine model-based control instead of model-free DDQN | iLQR controller · Atari Breakout | asymptotic reward | Hurt |
Closest papers by meaning
- PRDP: Progressively Refined Differentiable Physics (ICLR 2025 · similarity 0.88)
- Stabilizing Backpropagation Through Time to Learn Complex Physics (ICLR 2024 · similarity 0.87)
- Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods (ICLR 2025 · similarity 0.87)
- Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective (NeurIPS 2025 · similarity 0.86)
- ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks (ICLR 2025 · similarity 0.85)
- Mosaic: A Benchmark Suite for Differentiable Physics Solvers (NeurIPS 2026 · 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.