We investigate efficient exploration strategies of environments with unknown stochastic dynamics and sparse rewards. Specifically, we analyze first the impact of parallel simulations on the probability of reaching rare states within a finite time budget. Using simplified models based on random walks and L\'evy processes, we provide analytical results that demonstrate a phase transition in reaching probabilities as a function of the number of parallel simulations. We identify an optimal number of parallel simulations that balances exploration diversity and time allocation. Additionally, we analyze a restarting mechanism that exponentially enhances the probability of success by redirecting efforts toward more promising regions of the state space. Our findings contribute to a more qualitative and quantitative theory of some exploration schemes in reinforcement learning, offering insights into developing more efficient strategies for environments characterized by rare events.

In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs) to utilize external knowledge retrieved from external sources, our method adapts retrieval information to specific domains by employing CriticGPT to train a dedicated reward model. This reward model generates synthesized datasets for fine-tuning the RAG encoder, aligning its outputs more closely with human preferences. The versatility of our approach allows it to be effectively applied across various domains through domain-specific fine-tuning. We evaluate Reward-RAG on publicly available benchmarks from multiple domains, comparing it to state-of-the-art methods. Our experimental results demonstrate significant improvements in performance, highlighting the effectiveness of Reward-RAG in improving the relevance and quality of generated responses. These findings underscore the potential of integrating reward models with RAG to achieve superior outcomes in natural language generation tasks.

This paper examines the impact of fiscal incentives on industrial investment in Uruguay from 1974 to 2010. Using a mixed-method approach that combines econometric models with machine learning techniques, the study investigates both the short-term and long-term effects of fiscal benefits on industrial investment. The results confirm the significant role of fiscal incentives in driving long-term industrial growth, while also highlighting the importance of a stable macroeconomic environment, public investment, and access to credit. Machine learning models provide additional insights into nonlinear interactions between fiscal benefits and other macroeconomic factors, such as exchange rates, emphasizing the need for tailored fiscal policies. The findings have important policy implications, suggesting that fiscal incentives, when combined with broader economic reforms, can effectively promote industrial development in emerging economies.

This study explores human-robot interaction (HRI) based on a mobile robot and YOLO to increase real-time situation awareness and prevent accidents in the workplace. Using object segmentation, we propose an approach that is capable of analyzing these situations in real-time and providing useful information to avoid critical working situations. In the industry, ensuring the safety of workers is paramount, and solutions based on robots and AI can provide a safer environment. For that, we proposed a methodology evaluated with two different YOLO versions (YOLOv8 and YOLOv5) alongside a LoCoBot robot for supervision and to perform the interaction with a user. We show that our proposed approach is capable of navigating a test scenario and issuing alerts via Text-to-Speech when dangerous situations are faced, such as when hardhats and safety vests are not detected. Based on the results gathered, we can conclude that our system is capable of detecting and informing risk situations such as helmet/no helmet and safety vest/no safety vest situations.

We define a congruence that copes with null next-symbol probabilities that arise when the output of a language model is constrained by some means during text generation. We develop an algorithm for efficiently learning the quotient with respect to this congruence and evaluate it on case studies for analyzing statistical properties of LLM.

Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.

This paper introduces YamaS, a simulator integrating Unity3D Engine with Robotic Operating System for robot navigation research and aims to facilitate the development of both Deep Reinforcement Learning (Deep-RL) and Natural Language Processing (NLP). It supports single and multi-agent configurations with features like procedural environment generation, RGB vision, and dynamic obstacle navigation. Unique to YamaS is its ability to construct single and multi-agent environments, as well as generating agent's behaviour through textual descriptions. The simulator's fidelity is underscored by comparisons with the real-world Yamabiko Beego robot, demonstrating high accuracy in sensor simulations and spatial reasoning. Moreover, YamaS integrates Virtual Reality (VR) to augment Human-Robot Interaction (HRI) studies, providing an immersive platform for developers and researchers. This fusion establishes YamaS as a versatile and valuable tool for the development and testing of autonomous systems, contributing to the fields of robot simulation and AI-driven training methodologies.

Speculative Decoding is a widely used technique to speed up inference for Large Language Models (LLMs) without modifying its outcome. When performing inference on an LLM, speculative decoding uses a smaller draft model which generates speculative tokens and then uses the target LLM to verify those draft tokens. The speedup provided by speculative decoding heavily depends on the choice of the draft model. It has been widely suggested to select a draft model that provides a high probability of the generated token being accepted by the LLM to achieve the highest throughput. However, our experiments indicate the contrary with throughput diminishing as the probability of generated tokens to be accepted by the target model increases. To understand this phenomenon, we perform extensive experiments to characterize the different factors that affect speculative decoding and how those factors interact and affect the speedups. Based on our experiments we describe an analytical model which can be used to decide the right draft model for a given workload. Further, using our insights we design a new draft model for LLaMA-65B which can provide 30% higher throughput than existing draft models.

Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt over time to improve precision, introducing the concept of decoupling: shifting from point evaluation to data distribution. We use calibration strategies as strategy for decoupling machine learning (ML) classifiers from score-based actions within business logic frameworks. To evaluate these strategies, we perform a comparative analysis using a real-world business scenario and multiple ML models. Our findings highlight the trade-offs and performance implications of the approach, offering valuable insights for practitioners seeking to optimize their decoupling efforts. In particular, the Isotonic and Beta calibration methods stand out for scenarios in which there is shift between training and testing data.

While large language models (LLMs) have made considerable advancements in understanding and generating unstructured text, their application in structured data remains underexplored. Particularly, using LLMs for complex reasoning tasks on knowledge graphs (KGs) remains largely untouched. To address this, we propose KG-GPT, a multi-purpose framework leveraging LLMs for tasks employing KGs. KG-GPT comprises three steps: Sentence Segmentation, Graph Retrieval, and Inference, each aimed at partitioning sentences, retrieving relevant graph components, and deriving logical conclusions, respectively. We evaluate KG-GPT using KG-based fact verification and KGQA benchmarks, with the model showing competitive and robust performance, even outperforming several fully-supervised models. Our work, therefore, marks a significant step in unifying structured and unstructured data processing within the realm of LLMs.