Research map / Bandits and online learning / RL theory and MDPs
Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration
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 |
|---|---|---|---|
| Add clipping to RLSVI | RLSVI · Tabular finite-horizon MDP, worst-case | regret upper bound: \tilde{\mathrm{O}}(H^{5/2}S^{3/2}\sqrt{AT}) -> \tilde{\mathrm{O}}(H^2S\sqrt{AT}) | Helped |
| Add clipping to RLSVI | RLSVI · Tabular finite-horizon MDP, worst-case | high-probability regret guarantee | Helped |
| Use clipping during the early visitation phase | C-RLSVI · Tabular finite-horizon MDP, worst-case | regret upper bound | No clear effect |
Closest papers by meaning
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.90)
- Horizon-Free Regret for Linear Markov Decision Processes (ICLR 2024 · similarity 0.89)
- Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration (ICML 2025 · similarity 0.89)
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes (NeurIPS 2025 · similarity 0.89)
- Position: Constants are Critical in Regret Bounds for Reinforcement Learning (ICML 2025 · similarity 0.89)
- Achieving Tractable Minimax Optimal Regret in Average Reward MDPs (NeurIPS 2024 · similarity 0.88)
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.