João Dias

Manuel Guimarães, Joana Campos, Pedro A. Santos et al.

The deployment of Socially Intelligent Agents (SIAs) in learning environments has proven to have several advantages in different areas of application. Social Agent Authoring Tools allow scenario designers to create tailored experiences with high control over SIAs behaviour, however, on the flip side, this comes at a cost as the complexity of the scenarios and its authoring can become overbearing. In this paper we introduce the concept of Explainable Social Agent Authoring Tools with the goal of analysing if authoring tools for social agents are understandable and interpretable. To this end we examine whether an authoring tool, FAtiMA-Toolkit, is understandable and its authoring steps interpretable, from the point-of-view of the author. We conducted two user studies to quantitatively assess the Interpretability, Comprehensibility and Transparency of FAtiMA-Toolkit from the perspective of a scenario designer. One of the key findings is the fact that FAtiMA-Toolkit's conceptual model is, in general, understandable, however the emotional-based concepts were not as easily understood and used by the authors. Although there are some positive aspects regarding the explainability of FAtiMA-Toolkit, there is still progress to be made to achieve a fully explainable social agent authoring tool. We provide a set of key concepts and possible solutions that can guide developers to build such tools.

João Dias, Pedro A. Santos, Nuno Cordeiro et al.

While Artificial Intelligence applied to the legal domain is a topic with origins in the last century, recent advances in Artificial Intelligence are posed to revolutionize it. This work presents an overview and contextualizes the main advances on the field of Natural Language Processing and how these advances have been used to further the state of the art in legal text analysis.

Maria Duarte, Pedro A. Santos, João Dias et al.

Being able to clearly interpret legal texts and fully understanding our rights, obligations and other legal norms has become progressively more important in the digital society. However, simply giving citizens access to the laws is not enough, as there is a need to provide meaningful information that cater to their specific queries and needs. For this, it is necessary to extract the relevant semantic information present in legal texts. Thus, we introduce the SNR (Semantic Norm Recognition) system, an automatic semantic information extraction system trained on a domain-specific (legal) text corpus taken from Portuguese Consumer Law. The SNR system uses the Portuguese Bert (BERTimbau) and was trained on a legislative Portuguese corpus. We demonstrate how our system achieved good results (81.44\% F1-score) on this domain-specific corpus, despite existing noise, and how it can be used to improve downstream tasks such as information retrieval.

Vasco Nunes, João Dias, Pedro A. Santos

Maps are a very important component of strategy games, and a time-consuming task if done by hand. Maps generated by traditional PCG techniques such as Perlin noise or tile-based PCG techniques look unnatural and unappealing, thus not providing the best user experience for the players. However it is possible to have a generator that can create realistic and natural images of maps, given that it is trained how to do so. We propose a model for the generation of maps based on Generative Adversarial Networks (GAN). In our implementation we tested out different variants of GAN-based networks on a dataset of heightmaps. We conducted extensive empirical evaluation to determine the advantages and properties of each approach. The results obtained are promising, showing that it is indeed possible to generate realistic looking maps using this type of approach.

Samuel Mascarenhas, Manuel Guimarães, Pedro A. Santos et al.

More than a decade has passed since the development of FearNot!, an application designed to help children deal with bullying through role-playing with virtual characters. It was also the application that led to the creation of FAtiMA, an affective agent architecture for creating autonomous characters that can evoke empathic responses. In this paper, we describe FAtiMA Toolkit, a collection of open-source tools that is designed to help researchers, game developers and roboticists incorporate a computational model of emotion and decision-making in their work. The toolkit was developed with the goal of making FAtiMA more accessible, easier to incorporate into different projects and more flexible in its capabilities for human-agent interaction, based upon the experience gathered over the years across different virtual environments and human-robot interaction scenarios. As a result, this work makes several different contributions to the field of Agent-Based Architectures. More precisely, FAtiMA Toolkit's library based design allows developers to easily integrate it with other frameworks, its meta-cognitive model affords different internal reasoners and affective components and its explicit dialogue structure gives control to the author even within highly complex scenarios. To demonstrate the use of FAtiMA Toolkit, several different use cases where the toolkit was successfully applied are described and discussed.

Guilherme Palma, Pedro A. Santos, João Dias

Hex and Counter Wargames are adversarial two-player simulations of real military conflicts requiring complex strategic decision-making. Unlike classical board games, these games feature intricate terrain/unit interactions, unit stacking, large maps of varying sizes, and simultaneous move and combat decisions involving hundreds of units. This paper introduces a novel system designed to address the strategic complexity of Hex and Counter Wargames by integrating cutting-edge advancements in Recurrent Neural Networks with AlphaZero, a reliable modern Reinforcement Learning algorithm. The system utilizes a new Neural Network architecture developed from existing research, incorporating innovative state and action representations tailored to these specific game environments. With minimal training, our solution has shown promising results in typical scenarios, demonstrating the ability to generalize across different terrain and tactical situations. Additionally, we explore the system's potential to scale to larger map sizes. The developed system is openly accessible, facilitating continued research and exploration within this challenging domain.

Diogo S. Carvalho, Joana Campos, Manuel Guimarães et al.

Autonomous agents that can engage in social interactions witha human is the ultimate goal of a myriad of applications. A keychallenge in the design of these applications is to define the socialbehavior of the agent, which requires extensive content creation.In this research, we explore how we can leverage current state-of-the-art tools to make inferences about the emotional state ofa character in a story as events unfold, in a coherent way. Wepropose a character role-labelling approach to emotion tracking thataccounts for the semantics of emotions. We show that by identifyingactors and objects of events and considering the emotional stateof the characters, we can achieve better performance in this task,when compared to end-to-end approaches.

Tomás Alves, Samuel Gomes, João Dias et al.

Throughout the years, social norms have been promoted as an informal enforcement mechanism for achieving beneficial collective outcomes. Among the most used methods to foster interactions, framing the context of a situation or setting in-game rules have shown strong results as mediators on how an individual interacts with their peers. Nevertheless, we found that there is a lack of research regarding the use of incentives such as scores to promote social interactions differing in valence. Weighing how incentives influence in-game behavior, we propose the use of rewards to promote interactions varying in valence, i.e. positive or negative, in a two-player scenario. To do so, we defined social valence as a continuous scale with two poles represented by Complicate and Help. Then, we performed user tests where participants where asked to play a game with two reward-based systems to test on whether the scoring system influenced the social interaction valence. The results indicate that the developed reward-based systems were able to foster interactions diverging in social valence scores, providing insights on how factors such as incentives overlap individual's established social norms. These findings empower game developers and designers with a low-cost and effective policy tool that is able to promote in-game behavior changes.

Samuel Gomes, Tomás Alves, João Dias et al.

Recent research has taken particular interest in observing the dynamics between altruistic and individual behavior. This is a commonly approached problem when reasoning about social dilemmas, which have a plethora of real world counterparts in the fields of education, health and economics. Weighing how incentives influence in-game behavior, our study examines individual and altruistic interactions, by analyzing the players' strategies and interaction motives when facing different reward attribution strategies. Consequently, a model for interaction motives is also proposed, with the premise that the motives for interactions can be defined as a continuous space, ranging from self-oriented (associated to self-improvement behaviors) to others-oriented (associated to extreme altruism behaviors) motives. To evaluate the promotion of individual and altruistic behavior, we leverage Message Across, an in-loco two-player videogame with adaptable reward attribution systems. We conducted several user tests (N = 66) to verify to what extent individual and altruistic reward attribution systems led players to vary their strategies and motives orientation. Our results indicate that players' strategies and self-reported orientation of interaction motives varied highly significantly upon the deployment of individual and altruistic reward systems, which leads us to believe on the suitability of applying an incentive-based strategy to moderate the emergence of individual and altruistic behavior in games.

João Ribeiro, Francisco S. Melo, João Dias

In this paper we investigate two hypothesis regarding the use of deep reinforcement learning in multiple tasks. The first hypothesis is driven by the question of whether a deep reinforcement learning algorithm, trained on two similar tasks, is able to outperform two single-task, individually trained algorithms, by more efficiently learning a new, similar task, that none of the three algorithms has encountered before. The second hypothesis is driven by the question of whether the same multi-task deep RL algorithm, trained on two similar tasks and augmented with elastic weight consolidation (EWC), is able to retain similar performance on the new task, as a similar algorithm without EWC, whilst being able to overcome catastrophic forgetting in the two previous tasks. We show that a multi-task Asynchronous Advantage Actor-Critic (GA3C) algorithm, trained on Space Invaders and Demon Attack, is in fact able to outperform two single-tasks GA3C versions, trained individually for each single-task, when evaluated on a new, third task, namely, Phoenix. We also show that, when training two trained multi-task GA3C algorithms on the third task, if one is augmented with EWC, it is not only able to achieve similar performance on the new task, but also capable of overcoming a substantial amount of catastrophic forgetting on the two previous tasks.

Samuel Gomes, Carlos Martinho, João Dias

Nowadays, big effort is being put to study gamification and how game elements can be used to engage players. In this scope, we believe there is a growing need to explore the impact game mechanics have on the players' interactions and perception. This work focuses on the application of game mechanics to lead players to achieve certain types of social interaction (we named this type of mechanics social interaction mechanics). A word matching game called CrossAnt was modified so that it could dynamically generate different social interaction mechanics. These mechanics consisted in different key combinations needed to play the game and were aimed to promote what we think are three important types of social interactions: cooperation, competition and individual exploration. Our evaluation consisted on the execution of several sessions where two players interacted with the game for several levels and had to find for themselves how to perform the actions needed to succeed. While some of the levels required the input from both players in order to be completed, others could be completed by each player independently. Our results show that cooperation was perceived when both players had to intervene to perform the game actions. However, longer interactions may still be needed so that the other types of interactions are promoted.