Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1912.03973

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

Jalal Arabneydi·Amir G. Aghdam
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

math.OC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jalal Arabneydi, Amir G. Aghdam. 2020-06-02. Deep Teams: Decentralized Decision Making with Finite and Infinite Number of Agents. https://doi.org/10.1109/tac.2020.2966035

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

The Operational Impact of Registry size, Cycle length, and Blood Type Distribution in Multi-Registry Kidney Exchange Programs

Kidney exchange programs address donor recipient incompatibility by exchanging donors between incompatible pairs, but single center KEPs often suffer from limited donor pools, which reduce matching efficiency. Multi registry kidney exchange programs offer a promising solution but face challenges, including heterogeneous constraints across registries, cycle-length bounds, and data-sharing limitations. This study uses simulation to compare mKEP allocation against individual registry operation, contrasting unconstrained pooling with two safeguarded mechanisms: a cumulative individual-rationality guarantee and a Shapley value based fair-share mechanism. We examine how registry size, blood-type distribution, cycle-length bounds, and dropout probability affect the size and distribution of achievable gain. Our central finding is that the benefit of joining an mKEP is systematically uneven: under blood group composition asymmetry, the easier-to-match registry gains less than its partner even under both safeguarded mechanisms, and a larger registry gains less than a smaller one when pooled. A registry combining a larger arrival rate with an easier-to-match pool may see its gain under either safeguarded mechanism fall too small to be practically significant, while registries with a higher dropout rate see a larger benefit from pooling. This unevenness concentrates in O-type recipients: an easier-to-match registry sees fewer O-type transplants within itself under pooling, though O-type transplant rates rise system-wide. Tighter cycle-length bounds increase, rather than diminish, the relative transplant-volume benefit of pooling, while match quality is only modestly affected by any factor examined. These results highlight the importance of pairing multi-registry collaboration with a carefully designed, equitable benefit-sharing mechanism to keep participation attractive for all registries involved.

math.OC↗
arXiv2026

A polynomial approximation scheme for nonlinear model reduction by moment matching

We propose a procedure for the numerical approximation of invariance equations arising in the moment matching technique associated with reduced-order modeling of high-dimensional dynamical systems. The Galerkin residual method is employed to find an approximate solution to the invariance equation using a Newton iteration on the coefficients of a monomial basis expansion of the solution. These solutions to the invariance equations can then be used to construct reduced-order models. We assess the ability of the method to solve the invariance PDE system as well as to achieve moment matching and recover the steady-state behaviour of nonlinear systems with state dimension of order 1000 driven by linear and nonlinear signal generators.

math.OC↗
arXiv2026

Computationally Efficient Density-Driven Optimal Control via Analytical KKT Reduction and Contractive MPC

Efficient coordination for collective spatial distribution is a fundamental challenge in multi-agent systems. Prior research on Density-Driven Optimal Control (D2OC) established a framework to match agent trajectories to a desired spatial distribution. However, implementing this as a predictive controller requires solving a large-scale Karush-Kuhn-Tucker (KKT) system, whose computational complexity grows cubically with the prediction horizon. To resolve this, we propose an analytical structural reduction that transforms the T-horizon KKT system into a condensed quadratic program (QP). This formulation achieves O(T) linear scalability, significantly reducing the online computational burden compared to conventional O(T^3) approaches. Furthermore, to ensure rigorous convergence in dynamic environments, we incorporate a contractive Lyapunov constraint and prove the Input-to-State Stability (ISS) of the closed-loop system against reference propagation drift. Numerical simulations verify that the proposed method facilitates rapid density coverage with substantial computational speed-up, enabling long-horizon predictive control for large-scale multi-agent swarms.

math.OC↗