Research map / Probabilistic and scientific modeling / Dynamical systems
Neural Stochastic Control
Jingdong Zhang, Qunxi Zhu, Wei Lin
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 |
|---|---|---|---|
| Use AS instead of the linear controller with k=6.0 | stochastic control of the system f(x)=x log(1+x) · system f(x)=x log(1+x) | energy cost: 38,388 -> 1438 | Improved |
| Use AS instead of the linear controller with k=6.0 | stochastic control of the system f(x)=x log(1+x) · system f(x)=x log(1+x) | convergence speed | Improved |
| Use a nonlinear neural stochastic controller instead of linear control | harmonic linear oscillator · Harmonic Linear Oscillator | robustness | Improved |
| Use ES(+ICNN) instead of AS | harmonic linear oscillator · Harmonic Linear Oscillator | stability | Improved |
| Use the quadratic Lyapunov function instead of ICNN for ES (ablation) | ES · Harmonic Linear Oscillator | training time: 276.385s -> 78.071s | Improved |
| Use the quadratic Lyapunov function instead of ICNN for ES (ablation) | ES · Harmonic Linear Oscillator | distance at T=4: 1e-9 -> 0.049 | Hurt |
| Use the quadratic Lyapunov function instead of ICNN for ES (ablation) | ES · Harmonic Linear Oscillator | convergence time: 0.459 -> 3.683 | Hurt |
| Use AS instead of ES(+ICNN) | neural stochastic control · Harmonic Linear Oscillator | training time: 276.385s -> 4.839s | Improved |
| Use ES(+ICNN) instead of AS | neural stochastic control · Harmonic Linear Oscillator | convergence time: 2.027 -> 0.459 | Improved |
Closest papers by meaning
- FESSNC: Fast Exponentially Stable and Safe Neural Controller (ICML 2024 · similarity 0.88)
- Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions (AAAI 2024 · similarity 0.84)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.84)
- Deep learning for continuous-time stochastic control with jumps (NeurIPS 2025 · similarity 0.84)
- Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise (NeurIPS 2024 · similarity 0.83)
- Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation (ICML 2024 · similarity 0.83)
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.
