Research map / Bandits and online learning / RL theory and MDPs
Adversarial MDPs with bandit feedback
Achieve near-optimal regret in adversarial and delayed-feedback MDPs.
30 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in RL theory and MDPs, keyword cluster “markov decision · decision processes · processes mdps”
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.
7 papers in 2023–24 and 11 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 9.6% to 18.3%.
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
- 2019 · Online Convex Optimization in Adversarial Markov Decision Processes (ICML 2019 · 42 citations)
- 2020 · Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition (ICML 2020 · 26 citations)
- 2021 · The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition (NeurIPS 2021 · 0 citations)
- 2022 · Learning Adversarial Markov Decision Processes with Delayed Feedback (AAAI 2022 · 10 citations)
- 2023 · No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions (NeurIPS 2023 · 1 citation)
- 2024 · Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · 0 citations)
- 2025 · Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions (AAAI 2025 · 0 citations)
- 2026 · Data- and Variance-dependent Regret Bounds for Online Tabular MDPs (ICML 2026 · 0 citations)
Earliest papers here
- Online Convex Optimization in Adversarial Markov Decision Processes (ICML 2019 · 42 citations)
- Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function (NeurIPS 2019 · 22 citations)
- Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition (ICML 2020 · 26 citations)
What has been tried
21 papers here report 110 measured changes (a component added, removed or swapped, compared with a baseline): helped 80%, no clear effect 1%, hurt 13%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use the log-barrier regularizer instead of Tsallis entropy | Stochastic environments · regret bound | \sum (s \neq s_L, a \neq \pi^*(s)) \frac{\log T}{\Delta(s, a)} + \frac{L|S| \log T}{\Delta (\min)} -> \sum_{s \neq s_L, | Helped | Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback (NeurIPS 2025 · 0 citations) |
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).
- Shanghai Jiao Tong University · 3 papers
- University of Virginia · 2 papers
- Google · 2 papers
- Polytechnic Institute of Milan · 2 papers
- Politecnico di Milano · 2 papers
- University of Southern California · 2 papers
- The University of Tokyo · 2 papers
Use it
Download BibTeX of 27 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
- Average-reward and latent MDPs (57 papers)
- Non-stationary and structured MDPs (30 papers)
Elsewhere in the topic
- Regret bounds with function approximation (79 papers)
- Linear function approximation in RL (64 papers)
- Stochastic shortest path (11 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).