Research map / Bandits and online learning / RL theory and MDPs
Kernelized Reinforcement Learning with Order Optimal Regret Bounds
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 |
|---|---|---|---|
| Partition the state-action domain and fit kernel ridge regression using observations only from the same partition element | π-KRVI for RKHS episodic RL · RKHS episodic RL with polynomial eigendecay | regret: \mathcal{O}\left(H^2T^{\frac{d+\alpha\mathbin{/}2}{d+\alpha}}\log(T)\sqrt{\log\pa{\frac{H}{\delta}} } \right) | Helped |
| Use domain-partitioned kernel ridge regression with π-KRVI for Matérn kernels | π-KRVI · Kernelized bandits special case with Matérn kernels | regret: \mathcal{O}\left( H^2T^{\frac{\nu+d}{2\nu+d}} \log(T)\sqrt{\log\pa{\frac{H}{\delta}}} \right) | Helped |
Closest papers by meaning
- Kernel-Based Reinforcement Learning: A Finite-Time Analysis (ICML 2021 · similarity 0.93)
- Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm (NeurIPS 2024 · similarity 0.92)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.89)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Logarithmic Regret for Online KL-Regularized Reinforcement Learning (ICML 2025 · similarity 0.88)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 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.