Reinforcement learning-based sustainable educational intervention: An intelligent decision-making paradigm for global poverty reduction

Globally, there are many problems related to poverty and educational inequality. Because they are static and cannot easily adjust to changing situations, traditional approaches to better education frequently fail. In order to solve this issue, this paper uses reinforcement learning to create a sustainable educational intervention model. The intention is to use reinforcement learning in order to intelligently distribute educational resources and assist lessen poverty on a global scale by making better decisions. It is a model that the research develops to demonstrate how poverty and education are related. The model takes into account a number of variables, including socioeconomic status, poverty rates, and educational attainment. Then, in order to maximize the distribution of resources, a multi-agent decision-making method is created, in which families, governments, and schools collaborate. The study then presents sustainability indicators, such as environmental, and economic factors. These indicators are included in the reinforcement learning reward system, making sure that policies are always effective in the long run and able to adapt to the surroundings. In the experimental part, the model is tested by means of actual data and simulations, contrasting with more recent approaches and conventional approaches. The performance of the various approaches by using the MADDPG performs significantly better than the others. It particularly increases the amount of money spent by the government and has more measurable effects on the environment, particularly with regard to the use of resources and the efficacy of the entire policy. This work makes a useful and sensible approach to combating poverty on a global scale by moving from fixed to flexible solutions with the use of instructional tactics. Additionally, it offers helpful technical advice to support the Sustainable Development Goals (SDGs) of the UN.

Authors

Institutions

Publication Details

Published
2025-02-21
DOI
https://doi.org/10.1145/3729605.3729649
Primary Topic
Reinforcement Learning in Robotics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Reinforcement learning-based sustainable educational intervention: An intelligent decision-making paradigm for global poverty reduction

Mingxuan Du, Lin Wang, Mario Di Nardo
Reinforcement Learning in Robotics
article

Reinforcement learning-based sustainable educational intervention: An intelligent decision-making paradigm for global poverty reduction

Mingxuan Du, Lin Wang, Mario Di Nardo
article en

Abstract

Globally, there are many problems related to poverty and educational inequality. Because they are static and cannot easily adjust to changing situations, traditional approaches to better education frequently fail. In order to solve this issue, this paper uses reinforcement learning to create a sustainable educational intervention model. The intention is to use reinforcement learning in order to intelligently distribute educational resources and assist lessen poverty on a global scale by making better decisions. It is a model that the research develops to demonstrate how poverty and education are related. The model takes into account a number of variables, including socioeconomic status, poverty rates, and educational attainment. Then, in order to maximize the distribution of resources, a multi-agent decision-making method is created, in which families, governments, and schools collaborate. The study then presents sustainability indicators, such as environmental, and economic factors. These indicators are included in the reinforcement learning reward system, making sure that policies are always effective in the long run and able to adapt to the surroundings. In the experimental part, the model is tested by means of actual data and simulations, contrasting with more recent approaches and conventional approaches. The performance of the various approaches by using the MADDPG performs significantly better than the others. It particularly increases the amount of money spent by the government and has more measurable effects on the environment, particularly with regard to the use of resources and the efficacy of the entire policy. This work makes a useful and sensible approach to combating poverty on a global scale by moving from fixed to flexible solutions with the use of instructional tactics. Additionally, it offers helpful technical advice to support the Sustainable Development Goals (SDGs) of the UN.

Shinawatra University (TH), University of Naples Federico II (IT)
No poverty
Openalex Percentile: Top 95%
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.