Despite rapid progress in artificial intelligence, current systems struggle with the interconnected challenges that define real-world decision making. Practical domains, such as business management, require optimizing an open-ended and multi-faceted objective, actively learning environment dynamics from sparse experience, planning over long horizons in stochastic settings, and reasoning over spatial information. Yet existing human--AI benchmarks isolate subsets of these capabilities, limiting our ability to assess holistic decision-making competence. We introduce Mini Amusement Parks (MAPs), an amusement-park simulator designed to evaluate an agent's ability to model its environment, anticipate long-term consequences under uncertainty, and strategically operate a complex business. We provide human baselines and a comprehensive evaluation of state-of-the-art LLM agents, finding that humans outperform these systems by 6.5x on easy mode and 9.8x on medium mode. Our analysis reveals persistent weaknesses in long-horizon optimization, sample-efficient learning, spatial reasoning, and world modelling. By unifying these challenges within a single environment, MAPs offers a new foundation for benchmarking agents capable of adaptable decision making. Code: https://github.com/Skyfall-Research/MAPs

Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision.

The Stable Roommates problem with Ties and Incomplete lists (SRTI) is a matching problem characterized by the preferences of agents over other agents as roommates, where the preferences may have ties or be incomplete. SRTI asks for a matching that is stable and, sometimes, optimizes a domain-independent fairness criterion (e.g., Egalitarian). However, in real-world applications (e.g., assigning students as roommates at a dormitory), we usually consider a variety of domain-specific criteria depending on preferences over the habits and desires of the agents. With this motivation, we introduce a knowledge-based method to SRTI considering domain-specific knowledge, and investigate its real-world application for assigning students as roommates at a university dormitory. This paper is under consideration for acceptance in Theory and Practice of Logic Programming (TPLP).

As mentioned before, businesses across industries use AI-powered VMS to improve operations. Here are some of the industries that are making the most of their video analytics. Healthcare businesses can use video analytics to get details on whether or not the patients are being entertained with all the needs and requirements they need. In addition, other operations such as patient flow, admission process, guests, etc., can also be monitored to see the improvement opportunities. Retail businesses use video analytics to understand customer behavior and patterns to improve customer experience.

This article is part of "the philosophy of artificial intelligence," a series of posts that explore the ethical, moral, and social implications of AI today and in the future Last week, I wrote an analysis of "Reward Is Enough," a paper by scientists at DeepMind. As the title suggests, the researchers hypothesize that the right reward is all you need to create the abilities associated with intelligence, such as perception, motor functions, and language. This is in contrast with AI systems that try to replicate specific functions of natural intelligence such as classifying images, navigating physical environments, or completing sentences. The researchers go as far as suggesting that with well-defined reward, a complex environment, and the right reinforcement learning algorithm, we will be able to reach artificial general intelligence, the kind of problem-solving and cognitive abilities found in humans and, to a lesser degree, in animals. The article and the paper triggered a heated debate on social media, with reactions going from full support of the idea to outright rejection. Of course, both sides make valid claims.

Last week, I wrote an analysis of Reward Is Enough, a paper by scientists at DeepMind. As the title suggests, the researchers hypothesize that the right reward is all you need to create the abilities associated with intelligence, such as perception, motor functions, and language. This is in contrast with AI systems that try to replicate specific functions of natural intelligence such as classifying images, navigating physical environments, or completing sentences. The researchers go as far as suggesting that with well-defined reward, a complex environment, and the right reinforcement learning algorithm, we will be able to reach artificial general intelligence, the kind of problem-solving and cognitive abilities found in humans and, to a lesser degree, in animals. The article and the paper triggered a heated debate on social media, with reactions going from full support of the idea to outright rejection.

This article is part of "the philosophy of artificial intelligence," a series of posts that explore the ethical, moral, and social implications of AI today and in the future Last week, I wrote an analysis of "Reward Is Enough," a paper by scientists at DeepMind. As the title suggests, the researchers hypothesize that the right reward is all you need to create the abilities associated with intelligence, such as perception, motor functions, and language. This is in contrast with AI systems that try to replicate specific functions of natural intelligence such as classifying images, navigating physical environments, or completing sentences. The researchers go as far as suggesting that with well-defined reward, a complex environment, and the right reinforcement learning algorithm, we will be able to reach artificial general intelligence, the kind of problem-solving and cognitive abilities found in humans and, to a lesser degree, in animals. The article and the paper triggered a heated debate on social media, with reactions going from full support of the idea to outright rejection. Of course, both sides make valid claims.

The onset of Covid-19 spurred plenty of discussion and debate around topics such as cleanliness and contactless everything, but it also highlighted the growing role of AI automation. From leveraging AI to help diagnose Covid-19 and take on delivery coordination, to automating customer service its presence has been far more visible. Add to that economic cost savings pressures and companies will almost certainly expand the role of AI post-pandemic at a breakneck pace. Despite widespread phobias centered around AI taking jobs, its implementation will be overwhelmingly beneficial for employees and even save lives. A World Economic Forum (WEF) report stated that, although 75 million jobs are expected to be replaced by AI over the next three years, 133 million new roles will be created – a net gain of 58 million new jobs.

Demand-side management (DSM) in the smart grid allows customers to make autonomous decisions on their energy consumption, helping energy providers to reduce the peaks in load demand. The automated scheduling of smart devices in residential and commercial buildings plays a key role in DSM. Due to data privacy and user autonomy, such an approach is best implemented through distributed multi-agent systems. This paper makes the following contributions: (i) It introduces the Smart Home Device Scheduling (SHDS) problem, which formalizes the device scheduling and coordination problem across multiple smart homes as a multi-agent system; (ii) It describes a mapping of this problem to a distributed constraint optimization problem; (iii) It proposes a distributed algorithm for the SHDS problem; and (iv) It presents empirical results from a physically distributed system of Raspberry Pis, each capable of controlling smart devices through hardware interfaces.

On a previous post we learned how to train a machine learning classifier that is able to detect the different aspects mentioned on hotel reviews. With this aspect classifier, we were able to automatically know if a particular review was talking about cleanliness, comfort & facilities, food, Internet, location, staff and/or value for money. We also learned how to combine this classifier with the sentiment analysis classifier to get interesting insights and answer questions like are guests loving the location of a particular hotel but complaining about its cleanliness? These are the kind of questions we aim to answer with this tutorial and that will lead us to some interesting insights. The source code used for this process is available in this repository.