Research map / Reinforcement learning / Policy gradient and actor-critic
Spectral Learning from a Single Trajectory under Finite-State Policies
Borja Balle, Odalric-Ambrym Maillard
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 |
|---|---|---|---|
| Replace i.i.d. multi-trajectory Hankel estimation with a single-trajectory Cesaro-average Hankel estimator in spectral WFA learning | probabilistic automata (PFA) · theoretical analysis (single trajectory, mixing PFA) | Hankel matrix estimation error bound | No clear effect |
| Extend single-trajectory spectral learning from PFA to stochastic WFA via a cone-norm mixing analysis | stochastic weighted automata (SWFA) · theoretical analysis | concentration bound on Hankel matrix error | No clear effect |
Closest papers by meaning
- SpectraLDS: Provable Distillation for Linear Dynamical Systems (NeurIPS 2025 · similarity 0.86)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.85)
- Provable Length Generalization in Sequence Prediction via Spectral Filtering (ICML 2025 · similarity 0.85)
- Sequence Modeling with Spectral Mean Flows (NeurIPS 2025 · similarity 0.85)
- Universal Sequence Preconditioning (NeurIPS 2025 · similarity 0.84)
- The Power of Second Order Methods for Sequence Preconditioning (NeurIPS 2026 · similarity 0.84)
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.
