Adaptive Agents in Spatial Double-Auction Markets: Modeling the Emergence of Industrial Symbiosis

2025-12-19

AI Summary

Industrial symbiosis is constrained by socio-spatial frictions—including transportation costs and inefficient resource matching—yet existing models neglect the coupled effects of spatial structure, market mechanisms, and firms’ adaptive behaviors. To address this, we develop a spatially embedded double-auction multi-agent model integrating topological networks, deep Q-networks (DQN) and proximal policy optimization (PPO) reinforcement learning, and counterfactual regret minimization. The model simulates heterogeneous firms’ decentralized, locally driven decisions on by-product exchange. We demonstrate for the first time how stable, near-Nash equilibrium circulation patterns spontaneously emerge under resource scarcity and spatial constraints through decentralized coordination. Furthermore, we identify critical combinations of spatial density and market parameters that drive high circulation rates. Our findings provide quantifiable theoretical foundations and simulation-based evidence to inform incentive-compatible, sustainable industrial policy design.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Coordination and Collaboration
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Industrial symbiosis fosters circularity by enabling firms to repurpose residual resources, yet its emergence is constrained by socio-spatial frictions that shape costs, matching opportunities, and market efficiency. Existing models often overlook the interaction between spatial structure, market design, and adaptive firm behavior, limiting our understanding of where and how symbiosis arises. We develop an agent-based model where heterogeneous firms trade byproducts through a spatially embedded double-auction market, with prices and quantities emerging endogenously from local interactions. Leveraging reinforcement learning, firms adapt their bidding strategies to maximize profit while accounting for transport costs, disposal penalties, and resource scarcity. Simulation experiments reveal the economic and spatial conditions under which decentralized exchanges converge toward stable and efficient outcomes. Counterfactual regret analysis shows that sellers' strategies approach a near Nash equilibrium, while sensitivity analysis highlights how spatial structures and market parameters jointly govern circularity. Our model provides a basis for exploring policy interventions that seek to align firm incentives with sustainability goals, and more broadly demonstrates how decentralized coordination can emerge from adaptive agents in spatially constrained markets.

Problem

• Modeling industrial symbiosis emergence under socio-spatial constraints.
• Analyzing adaptive firm behavior in spatial double-auction markets.
• Exploring decentralized coordination for sustainable resource exchange.

Innovation

• Agent-based modeling with spatially embedded double-auction markets
• Reinforcement learning for adaptive bidding strategies in firms
• Counterfactual regret analysis to evaluate Nash equilibrium convergence