Research map / Bandits and online learning / Online convex optimization and games
Fast no-regret dynamics in games
Obtain near-constant regret and fast convergence via optimism and swap-regret analysis.
37 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Online convex optimization and games, keyword cluster “game · equilibrium · convergence”
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.
10 papers in 2023–24 and 9 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 4.4% to 3.3%.
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
- 2016 · Learning in Games: Robustness of Fast Convergence (NeurIPS 2016 · 44 citations)
- 2017 · Dynamic Thresholding and Pruning for Regret Minimization (AAAI 2017 · 39 citations)
- 2018 · Policy Regret in Repeated Games (NeurIPS 2018 · 5 citations)
- 2019 · Regret Circuits: Composability of Regret Minimizers (ICML 2019 · 13 citations)
- 2020 · Hedging in games: Faster convergence of external and swap regrets (NeurIPS 2020 · 10 citations)
- 2021 · Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions (AAAI 2021 · 17 citations)
- 2022 · Equilibrium Finding in Normal-Form Games via Greedy Regret Minimization (AAAI 2022 · 6 citations)
- 2023 · Regret Minimization and Convergence to Equilibria in General-sum Markov Games (ICML 2023 · 2 citations)
- 2024 · Learning Not to Regret (AAAI 2024 · 2 citations)
- 2025 · Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · 1 citation)
- 2026 · Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners (ICML 2026 · 0 citations)
Earliest papers here
- Learning in Games: Robustness of Fast Convergence (NeurIPS 2016 · 44 citations)
- Counterfactual Regret Minimization in Sequential Security Games (AAAI 2016 · 18 citations)
- Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games (NeurIPS 2016 · 6 citations)
What has been tried
28 papers here report 199 measured changes (a component added, removed or swapped, compared with a baseline): helped 69%, no clear effect 7%, hurt 18%, 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 |
|---|---|---|---|---|
| Add positive-part aggregation of instantaneous regrets | rock_paper_scissors (sampled) · convergence | Helped | Learning Not to Regret (AAAI 2024 · 2 citations) | |
| Use asymmetric initial conditions instead of symmetric initialization | Rock-Paper-Scissors · convergence to Nash equilibrium | Hurt | Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · 1 citation) | |
| increase the penalty factor λ | publishers' welfare · publishers' welfare | Mixed | On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions (ICLR 2025 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 19 papers; from OpenAlex and the papers' affiliations).
- Meta · 4 papers
- Carnegie Mellon University · 3 papers
- Google · 3 papers
- Google DeepMind · 2 papers
- Amazon · 2 papers
- Aarhus University · 2 papers
- Columbia University · 2 papers
- University of Southern California · 2 papers
- Singapore University of Technology and Design · 2 papers
- Massachusetts Institute of Technology · 2 papers
Use it
Download BibTeX of 30 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
- Last-iterate convergence in games (65 papers)
- Counterfactual regret minimization (15 papers)
Elsewhere in the topic
- Online learning with feedback graphs (155 papers)
- Best-of-both-worlds bandit algorithms (125 papers)
- Learning for pricing and auctions (101 papers)
- Constrained and unconstrained OCO algorithms (85 papers)
- Online decision-making with feedback structure (81 papers)
- Online allocation with constraints (77 papers)
- Learning-augmented online algorithms (73 papers)
- Dynamic and adaptive regret (57 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).