Abstract
Most modern solutions for video game balancing are directed towards specific games. We are currently researching general methods for automatic multiplayer game balancing. The problem is modeled as a meta-game, where game-play change the rules from another game. This way, a Machine Learning agent that learns to play a meta-game, learns how to change a base game following some balancing metric. But an issue resides in the generation of high volume of game-play training data, was agents of different skill compete against each other. For this end we propose the automatic generation of a population of surrogate agents by learning sampling. In Reinforcement Learning an agent learns in a trial error fashion where it improves gradually its policy, the mapping from world state to action to perform. This means that in each successful evolutionary step an agent follows a sub-optimal strategy, or eventually the optimal strategy. We store the agent policy at the end of each training episode. The process is evaluated in simple environments with distinct properties. Quality of the generated population is evaluated by the diversity of the difficulty the agents have in solving their tasks. © Springer Nature Switzerland AG 2019.

Abstract

Abstract

Abstract
In recent years, public institutions have undergone a progressive modernization process, bringing several administrative services to be provided electronically. Some institutions are responsible for analyzing citizen complaints, which come in huge numbers and are mainly provided in free-form text, demanding for some automatic way to process them, at least to some extent. In this work, we focus on the task of automatically identifying economic activities in complaints submitted to the Portuguese Economic and Food Safety Authority (ASAE), employing natural language processing (NLP) and machine learning (ML) techniques for Portuguese, which is a language with few resources. We formulate the task as several multi-class classification problems, taking into account the economic activity taxonomy used by ASAE. We employ features at the lexical, syntactic and semantic level using different ML algorithms. We report the results obtained to address this task and present a detailed analysis of the features that impact the performance of the system. Our best setting obtains an accuracy of 0.8164 using SVM. When looking at the three most probable classes according to the classifier’s prediction, we report an accuracy of 0.9474. © 2019, Springer Nature Switzerland AG.

Abstract

Abstract
Hazard Analysis and Critical Control Point (HACCP) system is based on a preventive methodology to avoid potential hazards that can cause harm and to ensure that unsafe food is not made available to consumers. This system is recognized by the Economic and Food Safety Authority, a criminal police responsible for food safety and economic inspection in Portugal. Every day, Economic and Food Safety Authority generates a large and complex volume of data from inspections and complaints, also in its classification, registration and in monitoring until the end of the process analysis. This study focuses on the reported entities that are related to non-compliance with HACCP, and tries to understand the most common infractions. Results show values between 30% and 37% related to non-compliance to HACCP. As main conclusions, from 2014 to 2018, the number of these infractions maintained the same level and it will be important to understand if the relationship between these problems are related to legislation understanding or application.