Research map / Probabilistic and scientific modeling / Variational and generative sampling
Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes
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 linear-MDP structure (efficient one-step estimator) instead of general nonparametric DRL estimator | OPE in linear MDP simulation · Simulated linear MDP (|S|=30, |A|=10, d=5, γ=0.8) | MSE and bias fluctuation vs DRL and DM | Helped |
| Cross-fitting / sample splitting in the one-step estimator (ablation) | Proposed one-step estimator · Simulated linear MDP (|S|=30, |A|=10, d=5, γ=0.8) | bias and MSE | No clear effect |
| Use the estimated variance to build 95% confidence intervals with sample size growing | Proposed one-step estimator · Simulated linear MDP (|S|=30, |A|=10, d=5, γ=0.8) | CI coverage rate | Helped |
Closest papers by meaning
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.92)
- Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models (NeurIPS 2021 · similarity 0.91)
- A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes (ICML 2022 · similarity 0.91)
- Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs (ICLR 2025 · similarity 0.88)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.87)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · 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.