Research map / Reinforcement learning / MDPs and planning
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
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 |
|---|---|---|---|
| plan on empirical MDP with reward perturbation (perturbed model-based planning) instead of unperturbed model-based planning | model-based RL with generative model · theory: sample size range for minimax optimality | minimum sample size for minimax-optimal guarantee | Helped |
| vary discount complexity 1/(1-gamma) and epsilon in a two-state MDP simulation | perturbed model-based planning · two-state MDP, 100 Monte Carlo runs | sample complexity per state-action pair | No clear effect |
Closest papers by meaning
- Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model (NeurIPS 2021 · similarity 0.95)
- Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning? (NeurIPS 2020 · similarity 0.92)
- Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model (NeurIPS 2018 · similarity 0.91)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 2024 · similarity 0.89)
- Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity (ICLR 2024 · similarity 0.89)
- Near-Optimal Sample Complexity for MDPs via Anchoring (ICML 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.