Research map / Bandits and online learning / RL theory and MDPs
Learning Stochastic Shortest Path with Linear Function Approximation
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 |
|---|---|---|---|
| Use Bernstein-type variance-aware confidence sets and weighted regression instead of Hoeffding-type confidence sets (ablation) | LEVIS for linear mixture SSP · Linear mixture SSP with positive minimum cost | regret: \tilde O(d B_{\star}^{1.5}\sqrt{K/c_{\min}}) -> \tilde O(dB_{\star}\sqrt{K/c_{\min}}) | Helped |
| Use cost perturbation with \rho=K^{-1/3} | LEVIS · Linear mixture SSP with general costs | regret: \tilde O(K^{2/3}) | Helped |
| Add time-step doubling as an update trigger alongside determinant doubling | LEVIS · Linear mixture SSP | regret | Helped |
Closest papers by meaning
- Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path (ICML 2023 · similarity 0.95)
- Near-optimal Regret Bounds for Stochastic Shortest Path (ICML 2020 · similarity 0.90)
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs (ICLR 2024 · similarity 0.88)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.87)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.87)
- Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs (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.