Research map / Bandits and online learning / RL theory and MDPs
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
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 expert knowledge of room translation invariance in the kernel metric (ablation) | Lip-UCBVI · Continuous two-room grid-world | sum of rewards / learning speed | Helped |
| Kernel-based (Lip-UCBVI) instead of uniform discretization baselines | Lip-UCBVI · Continuous two-room grid-world | sum of rewards | Helped |
| Larger kernel bias (bandwidth) for faster early learning, at cost of asymptotic performance | Lip-UCBVI · Continuous two-room grid-world | sum of rewards | Mixed |
| Replace full planning with RTDP-style incremental planning (Lip-UCBVI-Greedy) | Lip-UCBVI · Theory: regret bound | regret order | No clear effect |
Closest papers by meaning
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.91)
- Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm (NeurIPS 2024 · similarity 0.91)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · similarity 0.89)
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs (ICLR 2024 · similarity 0.88)
- Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation (NeurIPS 2024 · similarity 0.88)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 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.