Research map / Multi-agent systems and games / Games and equilibria
Mean-field game learning
Learns equilibria of mean-field games with reinforcement and imitation learning.
21 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Games and equilibria, keyword cluster “game · player · sum”
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.
5 papers in 2023–24 and 6 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 3.9% to 4.2%.
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 · Mean Field Multi-Agent Reinforcement Learning (ICML 2018 · 313 citations)
- 2019 · Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach (NeurIPS 2019 · 23 citations)
- 2020 · On the Convergence of Model Free Learning in Mean Field Games (AAAI 2020 · 55 citations)
- 2021 · Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time (ICML 2021 · 6 citations)
- 2022 · Generalization in Mean Field Games by Learning Master Policies (AAAI 2022 · 15 citations)
- 2023 · Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games (ICML 2023 · 2 citations)
- 2024 · Zero-Sum Games between Mean-Field Teams: Reachability-Based Analysis under Mean-Field Sharing (AAAI 2024 · 2 citations)
- 2025 · Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · 1 citation)
- 2026 · Population-Aware Imitation Learning in Mean-field Games with Common Noise (ICML 2026 · 0 citations)
Earliest papers here
- Mean Field Multi-Agent Reinforcement Learning (ICML 2018 · 313 citations)
- Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach (NeurIPS 2019 · 23 citations)
- Learning Mean-Field Games (NeurIPS 2019 · 7 citations)
What has been tried
17 papers here report 97 measured changes (a component added, removed or swapped, compared with a baseline): helped 70%, no clear effect 9%, hurt 14%, 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 |
|---|---|---|---|---|
| Increase the receding horizon | Random MFG · distance to full-horizon QπRE | Helped | Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · 1 citation) | |
| use a learning rate of 3 × 10⁻⁴ | center environment · training stability and convergence speed | 3 × 10⁻⁴ | Helped | Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics (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 11 papers; from OpenAlex and the papers' affiliations).
- ETHZ - ETH Zurich · 3 papers
- Google · 2 papers
- Swiss Federal Institute of Technology · 2 papers
- New York University · 2 papers
Use it
Download BibTeX of 21 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
- Learning in Markov games (111 papers)
- Cooperation and social dilemmas (95 papers)
- Opponent modeling in competitive games (75 papers)
Elsewhere in the topic
- Fair division and coalition formation (99 papers)
- Learning with strategic agents (74 papers)
- Strategic classification (51 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).