We introduce a principled method for performing zero-shot transfer in reinforcement learning (RL) by exploiting approximate models of the environment. Zero-shot transfer in RL has been investigated by leveraging methods rooted in generalized policy improvement (GPI) and successor features (SFs).

This study provides a comprehensive performance analysis of Data-Oriented Design (DOD) versus the traditional Object-Oriented Design (OOD), focusing on cache utilization and efficiency in multi-threaded environments. We developed and compared four distinct versions of the A* search algorithm: single-threaded OOD (ST -OOD), single-threaded DOD (ST -DOD), multi-threaded OOD (MT -OOD), and multi-threaded DOD (MT -DOD). The evaluation was based on metrics including execution time, memory usage, and CPU cache misses. In multi-threaded tests, the DOD implementation demonstrated considerable performance gains, with faster execution times and a lower number of raw system calls and cache misses. While OOD occasionally showed marginal advantages in memory usage or percentage-based cache miss rates, DOD's efficiency in data-intensive operations was more evident. Furthermore, our findings reveal that for a fine-grained task like the A* algorithm, the overhead associated with thread management led to single-threaded versions significantly outperforming their multi-threaded counterparts in both paradigms. We conclude that even when performance differences appear subtle in simple algorithms, the consistent advantages of DOD in critical metrics highlight its foundational architectural superiority, suggesting it is a more effective approach for maximizing hardware efficiency in complex, large-scale AI and parallel computing tasks.

As AI models continue to grow in complexity and size, so does the demand for vast computational resources and access to large-scale distributed datasets. At the same time, growing concerns about data privacy, ownership, and regulatory compliance make it increasingly difficult to centralize data for training. FL has emerged as a promising paradigm for addressing these challenges, enabling the training of collaborative models across multiple data silos without requiring the raw data to leave its source. While FL has gained traction in mobile and edge environments, such as smart-phones and IoT devices, its application in large-scale computing platforms like HPC clusters and cloud infrastructure remains underexplored. Meanwhile, the convergence of HPC and cloud computing is reshaping the landscape of modern data-intensive applications. These hybrid environments combine the raw power and efficiency of HPC with the scalability and flexibility of the cloud, making them well-suited for training large AI models. However, this integration brings new challenges: heterogeneous hardware (e.g., Central Processing Units (CPUs), Graphics Processing Units (GPUs), Tensor Processing Units (TPUs)), inconsistent network performance, dynamic resource availability, and non-uniform data distributions across clients. In this context, the deployment of federated learning across such mixed infrastructure is both a timely opportunity and a technical challenge. This paper explores how FL can be adapted and optimized to run efficiently across heterogeneous HPC and cloud environments, with a focus on scalability, system resilience, and performance under non-IID data conditions.

The ever-increasing number of Android devices and the accelerated evolution of malware, reaching over 35 million samples by 2024, highlight the critical importance of effective detection methods. Attackers are now using Artificial Intelligence to create sophisticated malware variations that can easily evade traditional detection techniques. Although machine learning has shown promise in malware classification, its success relies heavily on the availability of up-to-date, high-quality datasets. The scarcity and high cost of obtaining and labeling real malware samples presents significant challenges in developing robust detection models. In this paper, we propose MalSynGen, a Malware Synthetic Data Generation methodology that uses a conditional Generative Adversarial Network (cGAN) to generate synthetic tabular data. This data preserves the statistical properties of real-world data and improves the performance of Android malware classifiers. We evaluated the effectiveness of this approach using various datasets and metrics that assess the fidelity of the generated data, its utility in classification, and the computational efficiency of the process. Our experiments demonstrate that MalSynGen can generalize across different datasets, providing a viable solution to address the issues of obsolescence and low quality data in malware detection. With approximately 3 billion Android devices in operation worldwide [1], the mobile cybersecurity landscape faces formidable challenges. In 2024 alone, Kaspersky reported over 33.3 million cyberattacks targeting smartphone users globally, encompassing diverse forms of malware and unwanted software [2]. Adding to this problem, attackers are using Artificial Intelligence (AI) to rapidly generate new malware variants by exploiting patterns learned from existing malware [3].

Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. Experiments involving ten generative models and five balanced datasets demonstrate that the Super-Metric is more stable and consistent than traditional metrics, exhibiting stronger correlations with the actual performance of classifiers. Synthetic data generation has become an increasingly relevant strategy in cybersecurity [1], [2], [3], particularly as a way to mitigate the scarcity of real, complete, and high-quality datasets that limit the performance and generalization of machine learning models. Despite these advances, assessing the quality of synthetic data remains a complex and largely non-standardized methodological challenge [4], with no clear consensus on which metrics should be used or how to combine them consistently. The literature reports a significant fragmentation in the application of fidelity metrics, with studies identifying more than 65 distinct indicators used independently to assess fidelity [5]. This diversity hinders model-to-model comparison, reduces experimental reproducibility, and complicates the integrated interpretation of data quality.

Introduction: The application of Artificial Intelligence in games has evolved significantly, allowing for dynamic content generation. However, its use as a core gameplay co-creation tool remains underexplored. Objective: This paper proposes SpellForger, a game where players create custom spells by writing natural language prompts, aiming to provide a unique experience of personalization and creativity. Methodology: The system uses a supervised-trained BERT model to interpret player prompts. This model maps textual descriptions to one of many spell prefabs and balances their parameters (damage, cost, effects) to ensure competitive integrity. The game is developed in the Unity Game Engine, and the AI backend is in Python. Expected Results: W e expect to deliver a functional prototype that demonstrates the generation of spells in real time, applied to an engaging gameplay loop, where player creativity is central to the experience, validating the use of AI as a direct gameplay mechanic.

Binary options trading is often marketed as a field where predictive models can generate consistent profits. However, the inherent randomness and stochastic nature of binary options make price movements highly unpredictable, posing significant challenges for any forecasting approach. This study demonstrates that machine learning algorithms struggle to outperform a simple baseline in predicting binary options movements. Using a dataset of EUR/USD currency pairs from 2021 to 2023, we tested multiple models, including Random Forest, Logistic Regression, Gradient Boosting, and k-Nearest Neighbors (kNN), both before and after hyperparameter optimization. Furthermore, several neural network architectures, including Multi-Layer Perceptrons (MLP) and a Long Short-Term Memory (LSTM) network, were evaluated under different training conditions. Despite these exhaustive efforts, none of the models surpassed the ZeroR baseline accuracy, highlighting the inherent randomness of binary options. These findings reinforce the notion that binary options lack predictable patterns, making them unsuitable for machine learning-based forecasting.

Students often report difficulties in accessing day-to-day academic information, which is usually spread across numerous institutional documents and websites. This fragmentation results in a lack of clarity and causes confusion about routine university information. This project proposes the development of a chatbot using Generative Artificial Intelligence (GenAI) and Retrieval-Augmented Generation (RAG) to simplify access to such information. Several GenAI models were tested and evaluated based on quality metrics and the LLM-as-a-Judge approach. Among them, Gemini 2.0 Flash stood out for its quality and speed, and Gemma 3n for its good performance and open-source nature.

There are several reasons why reproducibility is often a challenge in RL.

Multi-task reinforcement learning aims to quickly identify solutions for new tasks with minimal or no additional interaction with the environment. Generalized Policy Improvement (GPI) addresses this by combining a set of base policies to produce a new one that is at least as good -- though not necessarily optimal -- as any individual base policy. Optimality can be ensured, particularly in the linear-reward case, via techniques that compute a Convex Coverage Set (CCS). However, these are computationally expensive and do not scale to complex domains. The Option Keyboard (OK) improves upon GPI by producing policies that are at least as good -- and often better. It achieves this through a learned meta-policy that dynamically combines base policies. However, its performance critically depends on the choice of base policies. This raises a key question: is there an optimal set of base policies -- an optimal behavior basis -- that enables zero-shot identification of optimal solutions for any linear tasks? We solve this open problem by introducing a novel method that efficiently constructs such an optimal behavior basis. We show that it significantly reduces the number of base policies needed to ensure optimality in new tasks. We also prove that it is strictly more expressive than a CCS, enabling particular classes of non-linear tasks to be solved optimally. We empirically evaluate our technique in challenging domains and show that it outperforms state-of-the-art approaches, increasingly so as task complexity increases.