Research map / Learning theory and algorithms / Sample complexity
Sample complexity of MDPs
Derives near-optimal sample bounds for reinforcement learning in discounted and average-reward Markov decision processes.
42 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Sample complexity, keyword cluster “sample complexity · pac · optimal sample”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
9 papers in 2023–24 and 9 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 2.7% to 2.7%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning (NeurIPS 2016)
- 2017 · Learning Linear Dynamical Systems via Spectral Filtering (NeurIPS 2017 · 5 citations)
- 2018 · SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation (ICML 2018 · 137 citations)
- 2019 · Sample-Optimal Parametric Q-Learning Using Linearly Additive Features (ICML 2019 · 101 citations)
- 2020 · Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction (NeurIPS 2020 · 59 citations)
- 2021 · Bilinear Classes: A Structural Framework for Provable Generalization in RL (ICML 2021 · 19 citations)
- 2022 · On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory (NeurIPS 2022 · 4 citations)
- 2023 · Global Convergence of Two-Timescale Actor-Critic for Solving Linear Quadratic Regulator (AAAI 2023 · 4 citations)
- 2024 · Optimal Sample Complexity for Average Reward Markov Decision Processes (ICLR 2024 · 1 citation)
- 2025 · Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation (AAAI 2025 · 0 citations)
- 2026 · The Optimal Sample Complexity of Linear Contracts (ICML 2026 · 0 citations)
Earliest papers here
- Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning (NeurIPS 2016)
- Learning Linear Dynamical Systems via Spectral Filtering (NeurIPS 2017 · 5 citations)
- SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation (ICML 2018 · 137 citations)
What has been tried
31 papers here report 164 measured changes (a component added, removed or swapped, compared with a baseline): helped 73%, no clear effect 9%, hurt 15%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 18 papers; from OpenAlex and the papers' affiliations).
- National University of Singapore · 2 papers
- Stanford University · 2 papers
- Peking University · 2 papers
- Purdue University · 2 papers
Use it
Download BibTeX of 32 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Sample complexity of learning distributions (101 papers)
- PAC learnability theory (79 papers)
- Sample complexity of ranking and selection (80 papers)
Elsewhere in the topic
- Minimax estimation rates (109 papers)
- Optimal mean estimation and subsampling (95 papers)
- Density and property estimation (86 papers)
- Statistical-query lower bounds (85 papers)
- Computational thresholds in graphs and structure (84 papers)
- Learning halfspaces under noise (84 papers)
- Robust and surrogate-loss learning bounds (83 papers)
- Learning under log-concave distributions (80 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).