Research map / Reinforcement learning / MDPs and planning
Nearly Horizon-Free Offline 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 a recursion-based bound on total variance in the plug-in estimator | Offline policy evaluation in time-homogeneous MDPs · Offline policy evaluation | value estimation error: \tilde{O}(\sqrt{\frac{1}{Kd_m}}) | Helped |
| Use model-based planning on the empirical MDP | Offline policy optimization in time-homogeneous MDPs · Offline policy optimization | sub-optimality gap: \widetilde{O}\left(\sqrt{\frac{1}{Kd_m}} + \frac{\min\{S, d\}}{Kd_m}\right) | Helped |
| Apply the prior time-homogeneous model-based planning bound instead of the proposed bound | Offline policy optimization for time-homogeneous linear MDPs · Offline policy optimization | sample complexity: \widetilde{O}\left(\frac{\min\{H, S, d\}}{d_m\epsilon^2}\right) -> \widetilde{O}\left(\frac{1}{d_m \epsilon^2} + \frac{\ | Hurt |
Closest papers by meaning
- A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs (ICML 2024 · similarity 0.92)
- Offline-Online Reinforcement Learning for Linear Mixture MDPs (NeurIPS 2026 · similarity 0.91)
- Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL (NeurIPS 2025 · similarity 0.91)
- Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff (NeurIPS 2024 · similarity 0.90)
- Worst-Case Offline Reinforcement Learning with Arbitrary Data Support (NeurIPS 2024 · similarity 0.90)
- On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage (NeurIPS 2026 · similarity 0.90)
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.