Research map / Probabilistic and scientific modeling / Dynamical systems
Stability of Controllers for Gaussian Process Forward Models
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 |
|---|---|---|---|
| theoretical stability region versus empirical rollout region for GP mean dynamics | proposed stability tool · mountain car and inverted pendulum | stability region | Mixed |
| moment matching (MM) versus numerical quadrature for uncertainty propagation | GP uncertain-input prediction · mountain car, 1.2s horizon | match to Monte Carlo distribution | Helped |
| NQ-based stability regions versus Monte Carlo regions for full GP distribution | NQ · mountain car and pendulum, 100s horizon | stability region | No clear effect |
| NQ versus long-horizon MC prediction runtime | NQ · 100s horizon | computation time | Helped |
| worst-case quadrature error bound from Lemma 3 | NQ · long horizons | practicality | Hurt |
Closest papers by meaning
- Safe Model-based Reinforcement Learning with Stability Guarantees (NeurIPS 2017 · similarity 0.85)
- Asynchronous Distributed Gaussian Process Regression (AAAI 2025 · similarity 0.84)
- Performative Control for Linear Dynamical Systems (NeurIPS 2024 · similarity 0.84)
- Exact Inference for Continuous-Time Gaussian Process Dynamics (AAAI 2024 · similarity 0.83)
- Safely Learning Controlled Stochastic Dynamics (NeurIPS 2025 · similarity 0.82)
- FESSNC: Fast Exponentially Stable and Safe Neural Controller (ICML 2024 · similarity 0.82)
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.