Research map / Multi-agent systems and games / Games and equilibria
Mean Field Multi-Agent Reinforcement Learning
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 |
|---|---|---|---|
| replace independent/frequency-based learners with mean field Q-learning (MF-Q) in many-agent setting | MF-Q · Gaussian Squeeze, N=500 and N=1000 | performance | Helped |
| use mean field approximation of neighbor actions (vs. full joint actions) | MF-Q · Battle game 64 v.s. 64 | win rate vs IL and AC | Helped |
| MAAC centralized critic baseline at large agent counts | MAAC · Gaussian Squeeze, N=500 and N=1000 | performance | Hurt |
| MF-Q versus MF-AC learning speed | MF-Q · Gaussian Squeeze and battle game | convergence speed | Helped |
| mean field Q-learning on Ising model via TD learning without energy function | MF-Q · Ising model 20x20 grid | order parameter vs temperature agreement with MCMC | Helped |
Closest papers by meaning
- Major-Minor Mean Field Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.90)
- Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation (ICLR 2025 · similarity 0.89)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.88)
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics (NeurIPS 2025 · similarity 0.88)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 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.