Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Agent-based Modeling meets the Capability Approach for Human Development: Simulating Homelessness Policy-making

Alba Aguilera, Nardine Osman, Georgina Curto

TL;DR

The work tackles homelessness by integrating the Capability Approach with agent-based modelling and reinforcement learning to evaluate policy options that expand or restore central capabilities. It formalizes CA as a Markov Decision Process, mapping resources, conversion factors, capabilities, and choice factors (values and needs) into states, actions, transitions, and dual-reward structures $Q_s(s,a)$ and $Q_l(s,a)$ with a policy $\\pi(a|s)$ and discount $\\gamma$. An ABM framework is proposed to simulate interactions among PEH, service providers, and regulators, enabling policy evaluation across multiple SDGs. The approach is demonstrated in a forthcoming health inequity case study in Barcelona, with data-informed, stakeholder-driven implementation and careful attention to ethics, privacy, and LNOB implications, aiming for a scalable, non-invasive tool for diverse social contexts.

Abstract

The global rise in homelessness calls for urgent and alternative policy solutions. Non-profits and governmental organizations alert about the many challenges faced by people experiencing homelessness (PEH), which include not only the lack of shelter but also the lack of opportunities for personal development. In this context, the capability approach (CA), which underpins the United Nations Sustainable Development Goals (SDGs), provides a comprehensive framework to assess inequity in terms of real opportunities. This paper explores how the CA can be combined with agent-based modelling and reinforcement learning. The goals are: (1) implementing the CA as a Markov Decision Process (MDP), (2) building on such MDP to develop a rich decision-making model that accounts for more complex motivators of behaviour, such as values and needs, and (3) developing an agent-based simulation framework that allows to assess alternative policies aiming to expand or restore people's capabilities. The framework is developed in a real case study of health inequity and homelessness, working in collaboration with stakeholders, non-profits and domain experts. The ultimate goal of the project is to develop a novel agent-based simulation framework, rooted in the CA, which can be replicated in a diversity of social contexts to assess policies in a non-invasive way.

Agent-based Modeling meets the Capability Approach for Human Development: Simulating Homelessness Policy-making

TL;DR

The work tackles homelessness by integrating the Capability Approach with agent-based modelling and reinforcement learning to evaluate policy options that expand or restore central capabilities. It formalizes CA as a Markov Decision Process, mapping resources, conversion factors, capabilities, and choice factors (values and needs) into states, actions, transitions, and dual-reward structures and with a policy and discount . An ABM framework is proposed to simulate interactions among PEH, service providers, and regulators, enabling policy evaluation across multiple SDGs. The approach is demonstrated in a forthcoming health inequity case study in Barcelona, with data-informed, stakeholder-driven implementation and careful attention to ethics, privacy, and LNOB implications, aiming for a scalable, non-invasive tool for diverse social contexts.

Abstract

The global rise in homelessness calls for urgent and alternative policy solutions. Non-profits and governmental organizations alert about the many challenges faced by people experiencing homelessness (PEH), which include not only the lack of shelter but also the lack of opportunities for personal development. In this context, the capability approach (CA), which underpins the United Nations Sustainable Development Goals (SDGs), provides a comprehensive framework to assess inequity in terms of real opportunities. This paper explores how the CA can be combined with agent-based modelling and reinforcement learning. The goals are: (1) implementing the CA as a Markov Decision Process (MDP), (2) building on such MDP to develop a rich decision-making model that accounts for more complex motivators of behaviour, such as values and needs, and (3) developing an agent-based simulation framework that allows to assess alternative policies aiming to expand or restore people's capabilities. The framework is developed in a real case study of health inequity and homelessness, working in collaboration with stakeholders, non-profits and domain experts. The ultimate goal of the project is to develop a novel agent-based simulation framework, rooted in the CA, which can be replicated in a diversity of social contexts to assess policies in a non-invasive way.

Paper Structure

This paper contains 14 sections, 1 equation, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The Capability Approach
  4. The CA in Agent-based Modelling
  5. Methods
  6. Example: The Difference a Bike Makes
  7. Proposed Choice Factors for an Enhanced Decision-Making Model
  8. The Capability Approach as a Markov Decision Process
  9. Towards Assessing Policies in terms of Capabilities with Agent-based Simulations
  10. Foreseen Case Study
  11. Health Inequity as a CA-based MDP
  12. Practical Implementation
  13. Implementation Plans, Evaluation and Expected Social Impact
  14. Challenges, Limitations and Ethical Considerations

Figures (2)

  • Figure 1: Schematic overview of the Capability Approach robyens2017 (in black), with the integration of computational elements to operationalize it in the agent-based modelling domain (in blue).
  • Figure 2: A Markov Decision Process (MDP) representation of the decision-making. Nodes represent states, while diamonds indicate actions that may be possible or impossible (i.e., capabilities or deprived capabilities) with lines and dashed lines, respectively.