Research map / Reinforcement learning / Policy gradient and actor-critic
Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction
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 abstract rather than ground state-action ratios | MIS OPE · TwoPath MDP | OPE estimate variance | Helped |
| Project states into an abstract state-space and estimate abstract ratios with BestDICE | BestDICE · High-dimensional state-space tasks | relative MSE | Helped |
| Use abstract rather than ground ratios | BestDICE · AntUMaze | relative MSE volatility across hyperparameter settings | Helped |
| Estimate abstract ratios with AbstractBestDICE | AbstractBestDICE · TwoPath MDP | abstract state-action density estimation accuracy | Helped |
Closest papers by meaning
- Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling (NeurIPS 2019 · similarity 0.94)
- Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation (ICML 2025 · similarity 0.92)
- Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies (ICLR 2024 · similarity 0.91)
- More Efficient Off-Policy Evaluation through Regularized Targeted Learning (ICML 2019 · similarity 0.91)
- Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs (ICLR 2025 · similarity 0.89)
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.89)
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.