BTUT
Planetary-scale multi-agent coordination through mean-field game theory. O(N) complexity. Provable convergence.
Mean-Field Game Theory
Population Distribution
Replace N² pairwise interactions with a continuous density function μ(x,t)
μ(x) = (1/N) Σᵢ δ(x - xᵢ)Kernel-Weighted Sensing
Agents sense local environment through Gaussian kernel weighting
K(x,y) = exp(-||x-y||² / 2σ²)Nash Equilibrium
System converges to equilibrium where no agent can unilaterally improve
ε = E[||uᵢ - u*||²] → 0Understanding the Equation
The Fokker-Planck equation describes how a population of agents evolves over time. Each term has an intuitive physical meaning.
∂μ/∂t = −∇·(μ v[μ]) + σ²ΔμRepresents the distribution of all agents across the state space. Instead of tracking each individual agent, we track the "crowd" as a continuous density.
The simulation progresses in discrete iterations. Each step, agents update their strategies based on what they observe from the population.
The "direction" each agent wants to move based on what they observe. Agents move toward better strategies by sensing the local population density.
Controls how much agents "explore" vs "exploit". Higher σ means more random exploration; lower σ means agents stick closer to their current strategy.
Measures how much the population "flows out" of a region. Positive divergence means agents are leaving; negative means they're concentrating.
Measures how "curved" the density is. Where density is peaked, the Laplacian is negative, causing spreading. This creates the diffusion effect.
Agents move toward better strategies. This is the "exploitation" term — following the gradient toward Nash equilibrium.
Random exploration spreads agents out. This is the "exploration" term — preventing premature convergence and ensuring global optimum discovery.
Think of it like a crowd at a concert. The drift term is everyone trying to get closer to the stage (optimization). The diffusion term is people randomly moving around (exploration). Together, they find the best viewing spots where everyone is satisfied — the Nash equilibrium.
Nash Gap (ε)
ε = E[||uᵢ − u*||²]The Nash gap measures how far agents are from the equilibrium strategy u*. When ε → 0, no agent can improve by changing their strategy unilaterally.
Application Areas
Build planetary-scale coordination
Connect real APIs, run live simulations, validate convergence.