Research map / Probabilistic and scientific modeling / Dynamical systems
An Efficient, Expressive and Local Minima-Free Method for Learning Controlled Dynamical Systems
Ahmed Hefny, Carlton Downey, Geoffrey Gordon
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 |
|---|---|---|---|
| Apply local BPTT refinement after initialization | RFF-PSR · Synthetic system, TORCS, simulated swimmer | mean square error | Improved |
| Initialize local refinement with two-stage regression rather than random parameters | RFF-PSR · Synthetic system, TORCS, simulated swimmer | mean square error | Improved |
| Use joint S1 instead of conditional S1 (ablation) | RFF-PSR · Synthetic system, TORCS, simulated swimmer | mean square error | No clear effect |
| Use RFF-PSR instead of HSE-PSR | RFF-PSR · Synthetic system | mean square error | Improved |
| Use RFF-PSR instead of the other tested methods under non-blind test policies | RFF-PSR · Simulated swimmer with non-blind test policies | mean square error | Improved |
Closest papers by meaning
- Improving Predictive State Representations via Gradient Descent (AAAI 2016 · similarity 0.88)
- State Sequences Prediction via Fourier Transform for Representation Learning (NeurIPS 2023 · similarity 0.88)
- Identifying latent state transitions in non-linear dynamical systems (ICLR 2025 · similarity 0.86)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.86)
- Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning (ICML 2024 · similarity 0.85)
- Safely Learning Controlled Stochastic Dynamics (NeurIPS 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.
