Agent-based models (ABMs) are simulation models used in economics to overcome some of the limitations of traditional frameworks based on general equilibrium assumptions. However, agents within an ABM follow predetermined, not fully rational, behavioural rules which can be cumbersome to design and difficult to justify. Here we leverage multi-agent reinforcement learning (RL) to expand the capabilities of ABMs with the introduction of fully rational agents that learn their policy by interacting with the environment and maximising a reward function. Specifically, we propose a 'Rational macro ABM' (R-MABM) framework by extending a paradigmatic macro ABM from the economic literature. We show that gradually substituting ABM firms in the model with RL agents, trained to maximise profits, allows for a thorough study of the impact of rationality on the economy. We find that RL agents spontaneously learn three distinct strategies for maximising profits, with the optimal strategy depending on the level of market competition and rationality. We also find that RL agents with independent policies, and without the ability to communicate with each other, spontaneously learn to segregate into different strategic groups, thus increasing market power and overall profits. Finally, we find that a higher degree of rationality in the economy always improves the macroeconomic environment as measured by total output, depending on the specific rational policy, this can come at the cost of higher instability. Our R-MABM framework is general, it allows for stable multi-agent learning, and represents a principled and robust direction to extend existing economic simulators.

Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating large language models into agent-based modeling and simulation presents a promising avenue for enhancing simulation capabilities. This paper surveys the landscape of utilizing large language models in agent-based modeling and simulation, examining their challenges and promising future directions. In this survey, since this is an interdisciplinary field, we first introduce the background of agent-based modeling and simulation and large language model-empowered agents. We then discuss the motivation for applying large language models to agent-based simulation and systematically analyze the challenges in environment perception, human alignment, action generation, and evaluation. Most importantly, we provide a comprehensive overview of the recent works of large language model-empowered agent-based modeling and simulation in multiple scenarios, which can be divided into four domains: cyber, physical, social, and hybrid, covering simulation of both real-world and virtual environments. Finally, since this area is new and quickly evolving, we discuss the open problems and promising future directions.

In economic modeling, there has been an increasing investigation into multi-agent simulators. Nevertheless, state-of-the-art studies establish the model based on reinforcement learning (RL) exclusively for specific agent categories, e.g., households, firms, or the government. It lacks concerns over the resulting adaptation of other pivotal agents, thereby disregarding the complex interactions within a real-world economic system. Furthermore, we pay attention to the vital role of the government policy in distributing tax credits. Instead of uniform distribution considered in state-of-the-art, it requires a well-designed strategy to reduce disparities among households and improve social welfare. To address these limitations, we propose an expansive multi-agent economic model comprising reinforcement learning agents of numerous types. Additionally, our research comprehensively explores the impact of tax credit allocation on household behavior and captures the spectrum of spending patterns that can be observed across diverse households. Further, we propose an innovative government policy to distribute tax credits, strategically leveraging insights from tax credit spending patterns. Simulation results illustrate the efficacy of the proposed government strategy in ameliorating inequalities across households.

The technology itself is fascinating, but part of what makes ChatGPT uniquely interesting is the fact that essentially overnight, most of the world gained access to a powerful generative artificial intelligence that they could use for their own purposes. In this episode of The Conversation Weekly, we speak with researchers who study computer science, technology and economics to explore how the rapid adoption of technologies has, for the most part, failed to change social and economic systems in the past – but why AI might be different, despite its weaknesses. Spending just a few minutes playing with new, generative AI algorithms can show you just how powerful they are. You can open up Dall-E, type in a phrase like "dinosaur riding motorcycle across a bridge," and seconds later, the algorithm will produce multiple images more or less depicting what you asked for. ChatGPT does much the same, just with text as its output.

New AI initiatives are utilizing synthetic intelligence to streamline the event course of by automating repetitive duties. While the purpose is to optimize effectivity, issues have been raised concerning the potential affect on employment charges and the economic system. This article explores the price of AI effectivity and the potential want for Universal Basic Income (UBI) as an answer. UXOS AI and different comparable initiatives are working to streamline the event course of and scale back growth time and value. It operates on the Binance Smart Chain community and creates a custom-made set of instruments to automate the event course of. While this strategy can considerably improve effectivity and pace up mission completion, there are issues concerning the potential affect on employment charges and the economic system usually.

You might be forgiven for thinking that the most important algorithm of the next decade will be graph neural networks. Or perhaps Bayesian inference will come to the fore, now that it has a Gartner-friendly name. Least squares will probably do more lifting than both, frankly, and let's not forget voting -- assuming anyone cares about the results of that (though I doubt the LinkedIn poll will prove to be the most important mechanism of our time). I invite you to consider another candidate. Let's play "What is this algorithm and where are the articles about it on Towards Data Science?" Its misfortune is the double one that it is not the product of human design and that the people guided by it usually do not know why they are made to do what they do.

Tackling the climate crisis is going to require a combined scientific, industrial, public and governmental effort on a scale that has never been seen before. It's little wonder, then, that the eyes of the world will be on Glasgow this weekend as COP26 gets underway. The goals of this UN climate change conference include reducing greenhouse gas emissions (with a target of global net zero by 2050), and protecting communities and natural habitats by making infrastructure and agriculture more resilient to future climate changes. Data science and artificial intelligence (AI) will have a crucial role to play in achieving these aims, allowing us to fully exploit the rapid growth in environmental data from sensors, remote sensing satellites and increasingly powerful numerical weather and climate models, to transform our understanding of the complex interactions between the environment, climate, ecosystems, and human social and economic systems. The sheer volume of data that needs to be assessed for developing sustainable pathways to net zero means that human decision-making needs to be augmented with AI.

My opinion on the subject of AI safety has to-and-fro'd from "not a concern" to "we are headed to our doom" to finally "it probably won't be as bad". My intention with this writeup is to provide some assurances that, although very much real, these risks would not become a concern if we assume that the basics of technical product development, safety engineering, and economic principles are followed. Let's first unpack what we mean by intelligence (artificial or not). Objectively, it is the ability to predict and/or to have control of the future for ones benefit. The farther the time horizon for this prediction and control, the more intelligent that entity is.

A polar bear on melting ice: It's a favorite image of nature documentaries and charity ads alike, never failing to put you in the emotional dumps for a simple reason--it forces you to grapple with a changing world, a darker future. But that emotion is often temporary, replaced quickly by others, because its effects are not immediately or directly felt, explained Peter Schlosser, the vice president and vice provost of global futures at Arizona State University. Footage of houses on fire in California, Oregon, and Australia alarms us, but falls short of making us understand that our own home may be next. These "delusions of escape," in the words of science fiction author Kim Stanley Robinson, or "failures of imagination," in the words of Future Tense academic director Ed Finn, placate us into reactive, piecemeal, short-sighted decision-making. But storytelling lights the path forward, agreed Robinson, Finn, Schlosser, Future Tense fellow Alexandra Zapata Hojel, and Malka Older, also a sci-fi author.

The COVID-19 pandemic is a dual crisis. On one hand, it is a global health crisis with millions of cases and hundreds of thousands of deaths. At the same time, decisions by individuals and governments in response to the pandemic have led to a severe economic slowdown, the likes of which has not seen since the Great Depression in the 20th century. But, as I wrote in a May 2020 column, economics can be argued to be one of the roots of this dual crisis. I quoted William Galston, who wrote: "What if the relentless pursuit of efficiency, which has dominated American business thinking for decades, has made the global economic system more vulnerable to shocks?"