Research map / Reinforcement learning / Offline RL
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning
Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 instance-dependent early stopping instead of the worst-case sample size | policy evaluation with ROOT-SA · Two-state MRP | sample size savings factor | Improved |
| make the instance easier (lambda 1.0 -> 1.5) (ablation) | early stopping procedure · Two-state MRP | sample size savings factor: lambda 1.0 -> 1.5 | Improved |
| use instance-dependent early stopping for Q-learning instead of worst-case sample size | Q-function estimation with ROOT-SA · MDP Example (epsilon 0.05) | sample size savings factor | Improved |
| compare predicted error against true error | error estimate of stopping rule · Two-state MRP (epsilon 0.1) | true error vs predicted error | No clear effect |
Closest papers by meaning
- On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation (AAAI 2023 · similarity 0.90)
- Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design (NeurIPS 2022 · similarity 0.90)
- Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs (NeurIPS 2024 · similarity 0.88)
- Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs (ICML 2024 · similarity 0.88)
- Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL (NeurIPS 2025 · similarity 0.87)
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.
