Mediating artificial intelligence developments through negative and positive incentives

Evolution of conditional cooperation in collective-risk social dilemma with repeated group interactions

The evolution and long-term sustenance of cooperation has consistently piqued scholarly interest across the disciplines of evolutionary biology and social sciences. Previous theoretical and experimental studies on collective risk social dilemma games have revealed that the risk of collective failure will affect the evolution of cooperation. In the real world, individuals usually adjust their decisions based on environmental factors such as risk intensity and cooperation level. However, it is still not well understood how such conditional behaviours affect the evolution of cooperation in repeated group interactions scenario from a theoretical perspective. Here, we construct an evolutionary game model with repeated interactions, in which defectors decide whether to cooperate in subsequent rounds of the game based on whether the risk exceeds their tolerance threshold and whether the number of cooperators exceeds the collective goal in the early rounds of the game. We find that the introduction of conditional cooperation strategy can effectively promote the emergence of cooperation, especially when the risk is low. In addition, the risk threshold significantly affects the evolutionary outcomes, with a high risk promoting the emergence of cooperation. Importantly, when the risk of failure to reach collective goals exceeds a certain threshold, the timely transition from a defective strategy to a cooperative strategy by conditional cooperators is beneficial for maintaining high-level cooperation.

Emergent behaviours in multi-agent systems with Evolutionary Game Theory

The mechanisms of emergence and evolution of collective behaviours in dynamical Multi-Agent Systems (MAS) of multiple interacting agents, with diverse behavioral strategies in co-presence, have been undergoing mathematical study via Evolutionary Game Theory (EGT). Their systematic study also resorts to agent-based modelling and simulation (ABM) techniques, thus enabling the study of aforesaid mechanisms under a variety of conditions, parameters, and alternative virtual games. This paper summarises some main research directions and challenges tackled in our group, using methods from EGT and ABM. These range from the introduction of cognitive and emotional mechanisms into agents’ implementation in an evolving MAS, to the cost-efficient interference for promoting prosocial behaviours in complex networks, to the regulation and governance of AI safety development ecology, and to the equilibrium analysis of random evolutionary multi-player games. This brief aims to sensitize the reader to EGT based issues, results and prospects, which are accruing in importance for the modeling of minds with machines and the engineering of prosocial behaviours in dynamical MAS, with impact on our understanding of the emergence and stability of collective behaviours. In all cases, important open problems in MAS research as viewed or prioritised by the group are described.

Indirect exclusion can promote cooperation in repeated group interactions

Social exclusion has been regarded as one of the most effective measures to promote the evolution of cooperation. In real society, the way in which social exclusion works can be direct or indirect. However, thus far there is no related work to explore how indirect exclusion influences the evolution of cooperation from a theoretical perspective. Here, we introduce indirect exclusion into the repeated public goods game where the game organizer probabilistically selects cooperators after the first game round to participate in the following possible game interactions. We then investigate the evolutionary dynamics of cooperation both in infinite and finite well-mixed populations. Through theoretical analysis and numerical calculations, we find that the introduction of indirect exclusion can induce the stable coexistence of cooperators and defectors or the dominance of cooperators, which thus effectively promotes the evolution of cooperation. Besides, we show that the identifying probability of the organizer has a nonlinear effect on public cooperation when its value is lower than an intermediate value, while the higher identifying probability can maintain a high level of cooperation. Furthermore, our results show that increasing the average rounds of game interactions can effectively promote the evolution of cooperation.

Early exclusion leads to cyclical cooperation in repeated group interactions

Explaining the emergence and maintenance of cooperation among selfish individuals from an evolutionary perspective remains a grand challenge in biology, economy and social sciences. Social exclusion is believed to be an answer to this conundrum. However, previously related studies often assume one-shot interactions and ignore how free-riding is identified, which seem to be too idealistic. In this work, we consider repeated interactions where excluders need to pay a monitoring cost to identify free-riders for exclusion and free-riders cannot participate in the following possible game interactions once they are identified and excluded by excluders in the repeated interaction process. We reveal that the introduction of such exclusion can prevent the breakdown of cooperation in repeated group interactions. In particular, we demonstrate that an evolutionary oscillation among cooperators, defectors and excluders can appear in infinitely large populations when early exclusion is implemented. In addition, we find that the population spends most of the time in states where cooperators dominate for early exclusion when stochastic mutation-selection is considered in finite populations. Our results highlight that early exclusion is successful in solving the mentioned enigma of cooperation in repeated group interactions.

Artificial intelligence development races in heterogeneous settings

Regulation of advanced technologies such as Artificial Intelligence (AI) has become increasingly important, given the associated risks and apparent ethical issues. With the great benefits promised from being able to first supply such technologies, safety precautions and societal consequences might be ignored or shortchanged in exchange for speeding up the development, therefore engendering a racing narrative among the developers. Starting from a game-theoretical model describing an idealised technology race in a fully connected world of players, here we investigate how different interaction structures among race participants can alter collective choices and requirements for regulatory actions. Our findings indicate that, when participants portray a strong diversity in terms of connections and peer-influence (e.g., when scale-free networks shape interactions among parties), the conflicts that exist in homogeneous settings are significantly reduced, thereby lessening the need for regulatory actions. Furthermore, our results suggest that technology governance and regulation may profit from the world's patent heterogeneity and inequality among firms and nations, so as to enable the design and implementation of meticulous interventions on a minority of participants, which is capable of influencing an entire population towards an ethical and sustainable use of advanced technologies.

Employing AI to Better Understand Our Morals

We present a summary of research that we have conducted employing AI to better understand human morality. This summary adumbrates theoretical fundamentals and considers how to regulate development of powerful new AI technologies. The latter research aim is benevolent AI, with fair distribution of benefits associated with the development of these and related technologies, avoiding disparities of power and wealth due to unregulated competition. Our approach avoids statistical models employed in other approaches to solve moral dilemmas, because these are "blind" to natural constraints on moral agents, and risk perpetuating mistakes. Instead, our approach employs, for instance, psychologically realistic counterfactual reasoning in group dynamics. The present paper reviews studies involving factors fundamental to human moral motivation, including egoism vs. altruism, commitment vs. defaulting, guilt vs. non-guilt, apology plus forgiveness, counterfactual collaboration, among other factors fundamental in the motivation of moral action. These being basic elements in most moral systems, our studies deliver generalizable conclusions that inform efforts to achieve greater sustainability and global benefit, regardless of cultural specificities in constituents.

Cost efficiency of institutional incentives for promoting cooperation in finite populations

Institutions can provide incentives to enhance cooperation in a population where this behaviour is infrequent. This process is costly, and it is thus important to optimize the overall spending. This problem can be mathematically formulated as a multi-objective optimization problem where one wishes to minimize the cost of providing incentives while ensuring a minimum level of cooperation, sustained over time. Prior works that consider this question usually omit the stochastic effects that drive population dynamics. In this paper, we provide a rigorous analysis of this optimization problem, in a finite population and stochastic setting, studying both pairwise and multi-player cooperation dilemmas. We prove the regularity of the cost functions for providing incentives over time, characterize their asymptotic limits (infinite population size, weak selection and large selection) and show exactly when reward or punishment is more cost efficient. We show that these cost functions exhibit a phase transition phenomenon when the intensity of selection varies. By determining the critical threshold of this phase transition, we provide exact calculations for the optimal cost of the incentive, for any given intensity of selection. Numerical simulations are also provided to demonstrate analytical observations. Overall, our analysis provides for the first time a selection-dependent calculation of the optimal cost of institutional incentives (for both reward and punishment) that guarantees a minimum level of cooperation over time. It is of crucial importance for real-world applications of institutional incentives since the intensity of selection is often found to be non-extreme and specific for a given population.

Combination of institutional incentives for cooperative governance of risky commons

Finding appropriate incentives to enforce collaborative efforts for governing the commons in risky situations is a long-lasting challenge. Previous works have demonstrated that both punishing free-riders and rewarding cooperators could be potential tools to reach this goal. Despite weak theoretical foundations, policy makers frequently impose a punishment-reward combination. Here, we consider the emergence of positive and negative incentives and analyze their simultaneous impact on sustaining risky commons. Importantly, we consider institutions with fixed and flexible incentives. We find that a local sanctioning scheme with pure reward is the optimal incentive strategy. It can drive the entire population toward a highly cooperative state in a broad range of parameters, independently of the type of institutions. We show that our finding is also valid for flexible incentives in the global sanctioning scheme, although the local arrangement works more effectively.

•

Pure reward in a local scheme is more effective both for fixed and flexible incentives

•

It can drive the entire population toward a highly cooperative state

•

Increasing the efficiency of the institution can induce the success of pure reward

•

A local scheme promotes group success more effectively than a global scheme