Research map / Learning theory and algorithms / Submodular and game algorithms
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply continuous-time Fictitious Play under the monotonicity assumption | Finite-horizon monotone MFGs · Finite-horizon MFGs | exploitability convergence rate: O(\frac{1}{t}) | Helped |
| Apply continuous-time Fictitious Play using γ-weighted occupancy measures | γ-discounted monotone MFGs · γ-discounted MFGs | exploitability convergence rate: O(\frac{1}{t}) | Helped |
| Extend continuous-time Fictitious Play to condition policies and distributions on common noise | Finite-horizon monotone MFGs · MFGs with common noise | exploitability convergence rate: O(\frac{1}{t}) | Helped |
| Use Backward Induction instead of Q-learning for best responses | Fictitious Play · Linear Quadratic MFG, finite horizon | exploitability convergence | Helped |
| Use Backward Induction instead of Q-learning for best responses | Fictitious Play · Beach Bar Process, finite horizon | exploitability convergence | Helped |
| Use Backward Induction instead of Q-learning for best responses | Fictitious Play · Linear Quadratic MFG with common noise | exploitability convergence | Helped |
| Use Backward Induction instead of Q-learning for best responses | Fictitious Play · Beach Bar Process with common noise | exploitability convergence | Helped |
| Use Backward Induction instead of Q-learning for best responses | Fictitious Play · Beach Bar Process, γ-discounted | exploitability convergence | Helped |
| Use Fictitious Play with model-based or model-free best-response computation | Fictitious Play · Beach Bar Process with common noise | Nash equilibrium convergence | Helped |
| Use model-based Policy Iteration rather than model-free Q-learning | Fictitious Play · Beach Bar Process, γ-discounted | final population distribution | No clear effect |
Closest papers by meaning
- Learning Discrete-Time Major-Minor Mean Field Games (AAAI 2024 · similarity 0.90)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · similarity 0.89)
- Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL (ICML 2024 · similarity 0.88)
- Last Iterate Convergence in Monotone Mean Field Games (NeurIPS 2025 · similarity 0.88)
- Last-iterate Convergence in Regularized Graphon Mean Field Game (AAAI 2025 · similarity 0.88)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.