Research map / Bandits and online learning / RL theory and MDPs
Stochastic shortest path
Derive minimax-optimal regret for stochastic shortest path problems.
11 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2020–2026) · an approach in RL theory and MDPs, keyword cluster “rl · function approximation · linear function”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
1 papers in 2023–24 and 1 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 1.4% to 1.7%.
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
- 2020 · Near-optimal Regret Bounds for Stochastic Shortest Path (ICML 2020 · 17 citations)
- 2021 · Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case (ICML 2021 · 5 citations)
- 2022 · Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation (ICML 2022 · 4 citations)
- 2023 · Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path (ICML 2023 · 0 citations)
- 2026 · OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal Regret (NeurIPS 2026)
Earliest papers here
- Near-optimal Regret Bounds for Stochastic Shortest Path (ICML 2020 · 17 citations)
- No-Regret Exploration in Goal-Oriented Reinforcement Learning (ICML 2020 · 13 citations)
- Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case (ICML 2021 · 5 citations)
What has been tried
8 papers here report 41 measured changes (a component added, removed or swapped, compared with a baseline): helped 71%, hurt 22%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 11 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
- Regret bounds with function approximation (79 papers)
- Linear function approximation in RL (64 papers)
Elsewhere in the topic
- Average-reward and latent MDPs (57 papers)
- Non-stationary and structured MDPs (30 papers)
- Adversarial MDPs with bandit feedback (30 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).