Deep Teams: Decentralized Decision Making with Finite and Infinite Number of Agents

TL;DR

This paper introduces deep teams, a framework for decentralized decision-making in multi-agent systems with sub-populations, providing polynomial complexity solutions and extending to infinite-horizon models, demonstrated through a service-management example.

Contribution

It develops novel dynamic programming methods for deep teams with polynomial complexity and extends the framework to infinite-horizon and asymmetric costs.

Findings

Polynomial complexity in number of agents and control horizon.

Convergence of computation and communication prices to zero.

Extension of results to infinite-horizon discounted models.

Abstract

Inspired by the concepts of deep learning in artificial intelligence and fairness in behavioural economics, we introduce deep teams in this paper. In such systems, agents are partitioned into a few sub-populations so that the dynamics and cost of agents in each sub-population is invariant to the indexing of agents. The goal of agents is to minimize a common cost function in such a manner that the agents in each sub-population are not discriminated or privileged by the way they are indexed. Two non-classical information structures are studied. In the first one, each agent observes its local state as well as the empirical distribution of the states of agents in each sub-population, called deep state, whereas in the second one, the deep states of a subset (possibly all) of sub-populations are not observed. Novel dynamic programs are developed to identify globally optimal and sub-optimal solutions for the first and second information structures, respectively. The computational complexity of finding the optimal solution in both space and time is polynomial (rather than exponential) with respect to the number of agents in each sub-population and is linear (rather than exponential) with respect to the control horizon. This complexity is further reduced in time by introducing a forward equation, that we call deep Chapman-Kolmogorov equation, described by multiple convolutional layers of Binomial probability distributions. Two different prices are defined for computation and communication, and it is shown that under mild assumptions they converge to zero as the quantization level and the number of agents tend to infinity. In addition, the main results are extended to the infinite-horizon discounted model and arbitrarily asymmetric cost function. Finally, a service-management example with 200 users is presented.