Although game design and adaptation are already challenging in single-player games due to the uncertainty of human behaviour, they become even more complex (but also more interesting) in multiplayer games given the human interaction they entail. Game research usually values how subjects with different characteristics perceive rewards and vary their conduct in single-player or competitive settings. The present study complements this by assessing how a player’s predisposition to share rewards in a cooperative scenario varies with their Agreeableness and Extraversion, as measured with the Five-Factor Model of personality. To this end, a two-player action role-playing game with a loot system named Cast Away was developed, and the actions of multiple pairs of players (N=40) were recorded. The behaviour and experience of different player personalities were tested, and a moment-by-moment analysis was conducted for game circumstances such as piking up potions or when a weapon was shared. Results support that the personality of another player has a greater impact on one’s behaviour and experience than their own, which was unexpected and challenges common multiplayer game design.

Psychology-oriented research extensively studied how affect influences human decision making. Particularly, the cognitive tuning assumption suggests that mood can serve to regulate between shallow and deliberative decisions – a more negative mood means higher deliberation. This work proposes a model that mimics the cognitive tuning assumption. To that end, the Collective Risk Dilemma (CRD) gameFor the Planetwas designed and created, a process allowing for distinct levels of reasoning was defined and tested in that game, and mood was integrated to control the level of reasoning of such a process. Several distinct Artificial Intelligence (AI) profiles were created to verify that the developed model was able to dynamically change the level of reasoning and adjust the resulting AI behavior in our CRD game. Results revealed that the distinct AI profiles were influenced by their affective states and experienced circumstances, and that the emergent behaviors were consistent with the cognitive tuning assumption, thus demonstrating that we managed to construct an innovative and flexible model that can use mood to dynamically adjust the level of reasoning of an AI agent.

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.

Abstract Understanding how to design agents that sustain cooperation in multi-agent systems has been a long-lasting goal in distributed artificial intelligence. Proposed solutions rely on identifying free-riders and avoiding cooperating or interacting with them. These mechanisms of social control are traditionally studied in games with linear and deterministic payoffs, such as the prisoner’s dilemma or the public goods game. In reality, however, agents often face dilemmas in which payoffs are uncertain and non-linear, as collective success requires a minimum number of cooperators. The collective risk dilemma (CRD) is one of these games, and it is unclear whether the known mechanisms of cooperation remain effective in this case. Here we study the emergence of cooperation in CRD through partner-based selection. First, we discuss an experiment in which groups of humans and robots play a CRD. This experiment suggests that people only prefer cooperative partners when they lose a previous game (i.e., when collective success was not previously achieved). Secondly, we develop an evolutionary game theoretical model pointing out the evolutionary advantages of preferring cooperative partners only when a previous game was lost. We show that this strategy constitutes a favorable balance between strictness (only interact with cooperators) and softness (cooperate and interact with everyone), thus suggesting a new way of designing agents that promote cooperation in CRD. We confirm these theoretical results through computer simulations considering a more complex strategy space. Third, resorting to online human–agent experiments, we observe that participants are more likely to accept playing in a group with one defector when they won in a previous CRD, when compared to participants that lost the game. These empirical results provide additional support to the human predisposition to use outcome-based partner selection strategies in human–agent interactions.

Serious games are moving towards multiplayer environments which aim to concurrently train and educate people. Therefore, we believe there is a growing need to construct systems which account for this tendency in order to ease learning and training. We here propose a model named Group Interactions Manager for Multiplayer sErious games (GIMME) which aims to improve the collective ability of players interacting in environments such as these. Our method organizes the players in groups and computes the types of interactions that should be promoted for each group. These interactions are then promoted by generating adequate game mechanics. We validate the most important aspects of the model by performing several agent-based simulations. The simulations suggest that learning can be improved when applying our strategy, as the average ability of the agents rapidly converged to high, near optimal values, as opposed to a random baseline (a strategy possibly implemented by real teachers when they do not know the students) which maintained low values. Moreover, unlike the random strategy, GIMME considerably approximated the promoted interactions profiles to the agents’ computed preferences.

This paper explores the role of prosocial behaviour when people team up with robots in a collaborative game that presents a social dilemma similar to a public goods game. An experiment was conducted with the proposed game in which each participant joined a team with a prosocial robot and a selfish robot. During 5 rounds of the game, each player chooses between contributing to the team goal (cooperate) or contributing to his individual goal (defect). The prosociality level of the robots only affects their strategies to play the game, as one always cooperates and the other always defects. We conducted a user study at the office of a large corporation with 70 participants where we manipulated the game result (winning or losing) in a between-subjects design. Results revealed two important considerations: (1) the prosocial robot was rated more positively in terms of its social attributes than the selfish robot, regardless of the game result; (2) the perception of competence, the responsibility attribution (blame/credit), and the preference for a future partner revealed significant differences only in the losing condition. These results yield important concerns for the creation of robotic partners, the understanding of group dynamics and, from a more general perspective, the promotion of a prosocial society.