Research map / Reinforcement learning / Offline RL
Leveraging Offline Data in Online Reinforcement Learning
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 offline data to initialize the online data buffer (FTPedel) instead of purely online exploration (Pedel) | FTPedel in linear MDPs · theoretical linear MDP analysis | online sample complexity | Helped |
| Offline data with poor coverage (dataset with 0 samples from suboptimal arms) combined with online exploration | FTPedel vs purely offline or purely online RL · explicit three-state MDP construction (Proposition on provable improvement) | online samples needed for epsilon-optimal policy: Ω(1/ε^2) for purely online reduced to O(1/ε^{8/5}) for FTPedel | Helped |
| Offline data covering only the optimal arm, with online verification of other arms | Verifiable RL in multi-armed bandit example · multi-armed bandit example | additional online samples needed from each suboptimal arm for verification | No clear effect |
Closest papers by meaning
- Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data (ICLR 2025 · similarity 0.93)
- Hybrid Reinforcement Learning from Offline Observation Alone (ICML 2024 · similarity 0.93)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.92)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.92)
- Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset (ICLR 2025 · similarity 0.92)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.92)
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.