Research map / Reinforcement learning / MDPs and planning
Policy optimization theory
Analyze policy finetuning, reward-free exploration, and effective horizon.
61 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · 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.
20 papers in 2023–24 and 12 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 9.9% to 6.9%.
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
- 2016 · Efficient Average Reward Reinforcement Learning Using Constant Shifting Values (AAAI 2016 · 25 citations)
- 2017 · Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting (NeurIPS 2017 · 23 citations)
- 2018 · Is Q-Learning Provably Efficient? (NeurIPS 2018 · 306 citations)
- 2019 · Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes (NeurIPS 2019 · 19 citations)
- 2020 · Provably Efficient Exploration in Policy Optimization (ICML 2020 · 80 citations)
- 2021 · Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning (NeurIPS 2021 · 16 citations)
- 2022 · Understanding Domain Randomization for Sim-to-real Transfer (ICLR 2022 · 33 citations)
- 2023 · Inverse Reinforcement Learning with the Average Reward Criterion (NeurIPS 2023 · 4 citations)
- 2024 · Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL (NeurIPS 2024 · 11 citations)
- 2025 · Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis (ICLR 2025 · 7 citations)
- 2026 · Constrained Meta Reinforcement Learning with Provable Test-Time Safety (ICML 2026 · 0 citations)
Earliest papers here
- Efficient Average Reward Reinforcement Learning Using Constant Shifting Values (AAAI 2016 · 25 citations)
- Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting (NeurIPS 2017 · 23 citations)
- Fairness in Reinforcement Learning (ICML 2017 · 7 citations)
What has been tried
41 papers here report 244 measured changes (a component added, removed or swapped, compared with a baseline): helped 64%, no clear effect 9%, hurt 22%, mixed 5%. 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 delay-adaptive lookahead technique | MuJoCo environments · reward performance | Hurt | Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis (ICLR 2025 · 7 citations) | |
| replace PACMAN clustering with KMeans++ | Meta-World zero-shot, 125K steps · success rate | 0.36 ± 0.07 -> 0.22 ± 0.06 | Hurt | Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks (ICML 2025 · 0 citations) |
| Increase lookahead depth h | DeepSea, exact setting · iterations to convergence | Helped | Policy Mirror Descent with Lookahead (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 32 papers; from OpenAlex and the papers' affiliations).
- University of California, Los Angeles · 3 papers
- Carnegie Mellon University · 3 papers
- Georgia Institute of Technology · 3 papers
- University of California, Berkeley · 2 papers
- ETHZ - ETH Zurich · 2 papers
- University of Pennsylvania · 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
- Function approximation in RL theory (93 papers)
- Offline RL sample complexity (86 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).