Research map / Reinforcement learning / Policy gradient and actor-critic
Markovian Interference in Experiments
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 |
|---|---|---|---|
| replace Naive estimator with DQ (difference in Q-functions) | Toy rental MDP estimators · Toy rental MDP (N=5000) | bias at t=10^4 N | Helped |
| use unbiased OPE estimators instead of DQ | Toy rental MDP estimators · Toy rental MDP (N=5000) | variance | Hurt |
| replace Naive with DQ | Ridesharing dispatch experiments · Ridesharing simulator (3 alpha values) | bias in ATE estimate | Helped |
| use two-sided randomization (TSR) designs instead of Naive | Ridesharing simulator · Ridesharing simulator | estimator error | No clear effect |
| use TSR designs instead of Naive | Toy rental MDP · Toy rental MDP (N=5000) | bias | Helped |
Closest papers by meaning
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.88)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.87)
- Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design (ICML 2024 · similarity 0.87)
- Beyond Expected Return: Accounting for Policy Reproducibility When Evaluating Reinforcement Learning Algorithms (AAAI 2024 · similarity 0.87)
- Doubly Optimal Policy Evaluation for Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Efficient Policy Evaluation Across Multiple Different Experimental Datasets (NeurIPS 2024 · similarity 0.86)
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.