Research map / Multi-agent systems and games / Games and equilibria
On Imitation in Mean-field Games
Giorgia Ramponi, Pavel Kolev, Olivier Pietquin, Niao He, Mathieu Lauriere, Matthieu Geist
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Replace vanilla adversarial IL (expert-population-driven) with MFC-ADV proxy that controls policy-induced occupancy measures | Adversarial imitation in MFGs · Attractor MFG, varying L and H | Nash imitation gap vs. proxy error | Improved |
| Increase population dependence of dynamics L (0.01 to 2) for BC | Behavioral cloning · Attractor MFG | Nash imitation gap vs. BC error | Hurt |
| Increase horizon H (3 to 100) for BC | Behavioral cloning · Attractor MFG | Nash imitation gap vs. BC error | Hurt |
| Increase L and H for vanilla-ADV | Vanilla adversarial IL · Attractor MFG | Nash imitation gap vs. vanilla-ADV error | Hurt |
| Use vanilla-ADV vs MFC-ADV at small L and H | Adversarial imitation · Attractor MFG, small L and H | Nash imitation gap | No clear effect |
| Use adversarial IL instead of BC when dynamics are population-independent (L_P=0) | MFG imitation · Theory, L_P=0 | Nash imitation gap bound horizon dependence | Improved |
| Make transition dynamics population-dependent (L_P>0) | BC and vanilla-ADV bounds · Theory | Nash imitation gap bound horizon dependence | Hurt |
Closest papers by meaning
- Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games (ICML 2025 · similarity 0.88)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.87)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · similarity 0.87)
- Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables (AAAI 2024 · similarity 0.87)
- Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL (ICML 2024 · similarity 0.87)
- Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games (NeurIPS 2026 · similarity 0.87)
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.
