Research map / Reinforcement learning / Policy gradient and actor-critic
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
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 |
|---|---|---|---|
| Bootstrap whole episodes instead of individual transitions | Bootstrapping FQE · Cliff Walking | error-distribution fidelity | Helped |
| Use subsampled bootstrap with subset size s=K^0.5 instead of vanilla bootstrap with s=K | Bootstrapping FQE · Cliff Walking | runtime | Helped |
| Use bootstrapping FQE instead of HCOPE | Off-policy confidence intervals · Cliff Walking | confidence-interval width | Helped |
| Use bootstrapping FQE instead of a concentration-based confidence interval | Off-policy confidence intervals · Mountain Car | confidence-interval width | Helped |
| Apply bootstrapping FQE with linear function approximation | FQE · Mountain Car | confidence-interval coverage | Helped |
| Apply bootstrapping FQE with neural-network function approximation | FQE · Sepsis management simulator | confidence-region estimation | Helped |
| Increase the difference between two target policies | Bootstrapping FQE correlation estimation · Sepsis management simulator | correlation between FQE estimators | Hurt |
| Use bootstrap confidence intervals with extremely small sample size (K=10) | Bootstrapping FQE · Cliff Walking | confidence-interval coverage | Hurt |
Closest papers by meaning
- Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction (NeurIPS 2019 · similarity 0.92)
- Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.89)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation (ICML 2024 · similarity 0.88)
- A Principled Path to Fitted Distributional Evaluation (NeurIPS 2025 · 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.