Research map / Reinforcement learning / MDPs and planning
Function approximation in RL theory
Establish sample-efficient RL with general and low-rank function approximation.
93 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in MDPs and planning, keyword cluster “sample complexity · function approximation · epsilon”
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.
37 papers in 2023–24 and 19 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 18.2% to 10.9%.
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
- 2018 · Learning the Reward Function for a Misspecified Model (ICML 2018 · 0 citations)
- 2019 · Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator (NeurIPS 2019 · 38 citations)
- 2020 · Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension (NeurIPS 2020 · 52 citations)
- 2021 · Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms (NeurIPS 2021 · 28 citations)
- 2022 · Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity (ICML 2022 · 8 citations)
- 2023 · On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration (NeurIPS 2023 · 5 citations)
- 2024 · Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo (ICLR 2024 · 5 citations)
- 2025 · Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach (ICML 2025 · 1 citation)
- 2026 · ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning (AAAI 2026 · 1 citation)
Earliest papers here
- Learning the Reward Function for a Misspecified Model (ICML 2018 · 0 citations)
- Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator (NeurIPS 2019 · 38 citations)
- Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle (NeurIPS 2019 · 35 citations)
What has been tried
66 papers here report 320 measured changes (a component added, removed or swapped, compared with a baseline): helped 70%, no clear effect 8%, hurt 16%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Remove the double Q trick | Atari games · performance | Hurt | Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo (ICLR 2024 · 5 citations) | |
| add a temporal shift to the oracle successor measure, especially with low-rank approximation | Medium PointMaze · accuracy | Helped | Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning (NeurIPS 2025 · 0 citations) | |
| threshold concatenated source features to retain d'' dimensions | Tucker rank (S, S, d), intersecting source feature subspaces · target regret bound dependence on feature dimension | dM to d'' | Helped | The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 56 papers; from OpenAlex and the papers' affiliations).
- University of California, Los Angeles · 6 papers
- Massachusetts Institute of Technology · 5 papers
- Princeton University · 4 papers
- Pennsylvania State University · 3 papers
- Google DeepMind · 3 papers
- University of Illinois, Urbana Champaign · 3 papers
- Peking University · 3 papers
- UC Santa Barbara · 2 papers
- University of California, Berkeley · 2 papers
- University of Science and Technology of China · 2 papers
Use it
Download BibTeX of 39 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
- Offline RL sample complexity (86 papers)
- Policy optimization theory (61 papers)
- Rich-observation exploration (53 papers)
Elsewhere in the topic
- Average-reward and regularized MDPs (135 papers)
- POMDPs and confounded RL (99 papers)
- Robust MDP policy gradient (87 papers)
- POMDP policy optimization (68 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).