Artificial intelligence meets minority game: toward optimal resource allocation

Abstract

Resource allocation systems provide the fundamental support for the normal functioning and well being of the modern society, and can be modeled as minority games. A ubiquitous dynamical phenomenon is the emergence of herding, where a vast majority of the users concentrate on a small number of resources, leading to a low efficiency in resource allocation. To devise strategies to prevent herding is thus of high interest. Previous works focused on control strategies that rely on external interventions, such as pinning control where a fraction of users are forced to choose a certain action. Is it possible to eliminate herding without any external control? The main point of this paper is to provide an affirmative answer through exploiting artificial intelligence (AI). In particular, we demonstrate that, when agents are empowered with reinforced learning in that they get familiar with the unknown game environment gradually and attempt to deliver the optimal actions to maximize the payoff, herding can effectively be eliminated. Computations reveal the striking phenomenon that, regardless of the initial state, the system evolves persistently and relentlessly toward the optimal state in which all resources are used efficiently. However, the evolution process is not without interruptions: there are large fluctuations that occur but only intermittently in time. The statistical distribution of the time between two successive fluctuating events is found to depend on the parity of the evolution, i.e., whether the number of time steps in between is odd or even. We develop a physical analysis and derive mean-field equations to gain an understanding of these phenomena. As minority game dynamics and the phenomenon of herding are common in social, economic, and political systems, and since AI is becoming increasingly widespread, we expect our AI empowered minority game system to have broad applications.

arXiv comment19pages,5 figures

References in corpus (25)

• Emergence of Cooperation and Organization in an Evolutionary Game
• Herd behavior and aggregate fluctuations in financial markets
• Transmission of Information and Herd Behavior: an Application to Financial Markets
• Effect of spatial structure on the evolution of cooperation
• Phase Transition and Symmetry Breaking in the Minority Game
• Coupled Replicator Equations for the Dynamics of Learning in Multiagent Systems
• Self-organized Networks of Competing Boolean Agents
• Competition in Social Networks: Emergence of a Scale-free Leadership Structure and Collective Efficiency
• Dynamics of Boltzmann Q-Learning in Two-Player Two-Action Games
• Emergence of time-horizon invariant correlation structure in financial returns by subtraction of the market mode
• Crowd-anticrowd theory of the Minority Game
• Effects of Contrarians in the Minority Game
• Self-organized Boolean game on networks
• Adaptive Boolean Networks and Minority Games with Time--Dependent Capacities
• Theory of Networked Minority Games based on Strategy Pattern Dynamics
• Clustering Evolutionary Stock Market Model
• Adaptive drivers in a model of urban traffic
• Theory of enhanced performance emerging in a sparsely-connected competitive population
• Harms and benefits from social imitation
• Global Optimization of Minority Game by Smart Agents
• Stylized facts in minority games with memory: a new challenge
• Self adaptation of chimera states
• Dynamical instabilities in a simple minority game with discounting
• Self-organization in populations of competing agents
• Coevolutionary networks of reinforcement-learning agents

Cited by in corpus (10)

• Evolution of cooperation in the public goods game with Q-learning
• Emergence of cooperation under punishment: A reinforcement learning perspective
• Decoding trust: A reinforcement learning perspective
• Catalytic evolution of cooperation in a population with behavioural bimodality
• Optimal coordination of resources: A solution from reinforcement learning
• Decoding fairness: a reinforcement learning perspective
• Evolution of cooperation with Q-learning: the impact of information perception
• Evolution of cooperation in a bimodal mixture of conditional cooperators
• Evolutionary dynamics in financial markets with heterogeneities in strategies and risk tolerance
• Modelling resource allocation in uncertain system environment through deep reinforcement learning