Research map / Bandits and online learning / RL theory and MDPs
Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
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 |
|---|---|---|---|
| Replace variance-only weights (LEVIS+) with variance- and uncertainty-aware weights plus high-order moment estimation, removing c_min/T* dependence | linear mixture SSP regret · theoretical regret bound | regret upper bound order | Helped |
| Use the proposed weighted regression with high-order moment variance estimation in place of LEVIS+ weights | synthetic two-state linear mixture SSP · Appendix B synthetic SSP (B*=3) | average regret R_K/K | Helped |
Closest papers by meaning
- Learning Stochastic Shortest Path with Linear Function Approximation (ICML 2022 · similarity 0.95)
- Minimax Regret for Stochastic Shortest Path (NeurIPS 2021 · similarity 0.93)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs (NeurIPS 2024 · similarity 0.89)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.88)
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback (NeurIPS 2024 · similarity 0.87)
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.