Publications

Setting the right goals and prioritizing them might be the most crucial and the most challenging type of decisions people make for themselves, their teams, and their organizations. In this article, we explore whether it might be possible to leverage artificial intelligence (AI) to help people set better goals and which potential problems might arise from such applications. We devised the first prototype of an AI-powered digital goal-setting assistant and a rigorous empirical paradigm for assessing the quality of AI-generated goal suggestions. Our empirical paradigm compares the AI-generated goal suggestions against randomly-generated goal suggestions and unassisted goal-setting on a battery of self-report measures of important goal characteristics, motivation, and usability in a large-scale repeated-measures online experiment. The results of an online experiment with 259 participants revealed that our intuitively compelling goal suggestion algorithm was actively harmful to the quality of the people's goals and their motivation to pursue them. These surprising findings highlight three crucial problems to be tackled by future work on leveraging AI to help people set better goals: i) aligning the objective function of the AI algorithms with the design goals, ii) helping people quantify how valuable different goals are to them, and iii) preserving the user's sense of autonomy.

People’s intentional pursuit of prosocial goals and values (i.e., well-doing) is critical to the flourishing of humanity in the long run. Understanding and promoting well-doing is a shared goal across many fields inside and outside of social and personality psychology. Several of these fields are (partially) disconnected from each other and could benefit from more integration of existing knowledge, interdisciplinary collaboration, and cross-fertilization. To foster the transfer and integration of knowledge across these different fields, we provide a brief overview with pointers to some of the key articles in each field, highlight connections, and introduce an integrative model of the psychological mechanisms of well-doing. We identify some gaps in the current understanding of well-doing, such as the paucity of research on well-doing with large and long-lasting positive consequences. Building on this analysis, we identify opportunities for high-impact research on well-doing in social and personality psychology, such as understanding and promoting the effective pursuit of highly impactful altruistic goals.

Human decision-making is plagued by many systematic errors. Many of these errors can be avoided by providing decision aids that guide decision-makers to attend to the important information and integrate it according to a rational decision strategy. Designing such decision aids is a tedious manual process. Advances in cognitive science might make it possible to automate this process in the future. We recently introduced machine learning methods for discovering optimal strategies for human decision-making automatically and an automatic method for explaining those strategies to people. Decision aids constructed by this method were able to improve human decision-making. However, following the descriptions generated by this method is very tedious. We hypothesized that this problem can be overcome by conveying the automatically discovered decision strategy as a series of natural language instructions for how to reach a decision. Experiment 1 showed that people do indeed understand such procedural instructions more easily than the decision aids generated by our previous method. Encouraged by this finding, we developed an algorithm for translating the output of our previous method into procedural instructions. We applied the improved method to automatically generate decision aids for a naturalistic planning task (i.e., planning a road trip) and a naturalistic decision task (i.e., choosing a mortgage). Experiment 2 showed that these automatically generated decision-aids significantly improved people's performance in planning a road trip and choosing a mortgage. These findings suggest that AI-powered boosting has potential for improving human decision-making in the real world.

Teaching people clever heuristics is a promising approach to improve decision-making under uncertainty. The theory of resource-rationality makes it possible to leverage machine learning to discover optimal heuristics automatically. One bottleneck of this approach is that the resulting decision strategies are only as good as the model of the decision-problem that the machine learning methods were applied to. This is problematic because even domain experts cannot give complete and fully accurate descriptions of the decisions they face. To address this problem, we develop strategy discovery methods that are robust to potential inaccuracies in the description of the scenarios in which people will use the discovered decision strategies. The basic idea is to derive the strategy that will perform best in expectation across all possible real-world problems that could have given rise to the likely erroneous description that a domain expert provided. To achieve this, our method uses a probabilistic model of how the description of a decision problem might be corrupted by biases in human judgment and memory. Our method uses this model to perform Bayesian inference on which real-world scenarios might have given rise to the provided descriptions. We applied our Bayesian approach to robust strategy discovery in two domains: planning and risky choice. In both applications, we find that our approach is more robust to errors in the description of the decision problem and that teaching the strategies it discovers significantly improves human decision-making in scenarios where approaches ignoring the risk that the description might be incorrect are ineffective or even harmful. The methods developed in this article are an important step towards leveraging machine learning to improve human decision-making in the real world because they tackle the problem that the real world is fundamentally uncertain.

To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful for understanding and improving human decision-making. But our ability to compute those strategies used to be limited to very small and very simple planning tasks. To overcome this computational bottleneck, we introduce a cognitively-inspired reinforcement learning method that can overcome this limitation by exploiting the hierarchical structure of human behavior. The basic idea is to decompose sequential decision problems into two sub-problems: setting a goal and planning how to achieve it. This hierarchical decomposition enables us to discover optimal strategies for human planning in larger and more complex tasks than was previously possible. The discovered strategies outperform existing planning algorithms and achieve a super-human level of computational efficiency. We demonstrate that teaching people to use those strategies significantly improves their performance in sequential decision-making tasks that require planning up to eight steps ahead. By contrast, none of the previous approaches was able to improve human performance on these problems. These findings suggest that our cognitively-informed approach makes it possible to leverage reinforcement learning to improve human decision-making in complex sequential decision-problems. Future work can leverage our method to develop decision support systems that improve human decision making in the real world.

Making good decisions requires thinking ahead, but the huge number of actions and outcomes one could consider makes exhaustive planning infeasible for computationally constrained agents, such as humans. How people are nevertheless able to solve novel problems when their actions have long-reaching consequences is thus a long-standing question in cognitive science. To address this question, we propose a model of resource-constrained planning that allows us to derive optimal planning strategies. We find that previously proposed heuristics such as best-first search are near-optimal under some circumstances, but not others. In a mouse-tracking paradigm, we show that people adapt their planning strategies accordingly, planning in a manner that is broadly consistent with the optimal model but not with any single heuristic model. We also find systematic deviations from the optimal model that might result from additional cognitive constraints that are yet to be uncovered.

Human decision making is plagued by systematic errors that can have devastating consequences. Previous research has found that such errors can be partly prevented by teaching people decision strategies that would allow them to make better choices in specific situations. Three bottlenecks of this approach are our limited knowledge of effective decision strategies, the limited transfer of learning beyond the trained task, and the challenge of efficiently teaching good decision strategies to a large number of people. We introduce a general approach to solving these problems that leverages artificial intelligence to discover and teach optimal decision strategies. As a proof of concept, we developed an intelligent tutor that teaches people the automatically discovered optimal heuristic for environments where immediate rewards do not predict long-term outcomes. We found that practice with our intelligent tutor was more effective than conventional approaches to improving human decision making. The benefits of training with our cognitive tutor transferred to a more challenging task and were retained over time. Our general approach to improving human decision making by developing intelligent tutors also proved successful for another environment with a very different reward structure. These findings suggest that leveraging artificial intelligence to discover and teach optimal cognitive strategies is a promising approach to improving human judgment and decision making.

Nowadays, more people can access digital educational resources than ever before. However, access alone is often not sufficient for learners to fulfil their learning goals. To support motivation, learning environments are often gamified, meaning that they offer points for interacting with them. But gamification can add to learners’ tendencies to choose learning activities in a short-sighted manner. An example for a short-sighted choice bias is the preference for an easy task offering a quick sense of accomplishment (and in gamified environments often a quick accumulation of points) over a harder task offering to make real progress. The concept of optimal brain points demonstrates that methods from the field of reinforcement learning, specifically reward shaping, allow us to align short-term rewards for learning choices with their expected long-term benefit in a learning context. Building on that work, we here present a scalable approach to supporting self-directed learning in digital learning environments applicable to real-world educational games. It can motivate learners to choose the learning activities that are most beneficial for them in the long run. This is achieved by incentivizing each learning activity in a way that reflects how much progress can be made by completing it and how that progress relates to their learning goal. Specifically, the approach entails modelling how learners choose between learning activities as a Markov Decision Process and applying methods from reinforcement learning to compute which learning choices optimize the learners progress based on their current knowledge. We specify how our developed method can be applied to the English-learning App “Dawn of Civilisation”. We further present the first evaluation of the approach in a controlled online experiment with a simplified learning task, which showed that the derived incentives can significantly improve both learners’ choice behaviour and their learning outcomes.

Negative emotions can make maladaptive behavior more likely, especially when people have poor emotion regulation and metacognitive skills (ERMSs). We developed an app to help non-clinical populations train and apply good ERMSs. The app teaches ERMSs with the help of gamified features such as customizable emotion avatars and points for practicing ERMSs. In an initial, brief pre/post test of the app, 60 participants used it to reflect on a difficult emotional challenge and (non-)beneficial ways of acting. Then, they completed a metacognitive skill-building module. After using the app, participants' scores showed significantly decreased/increased perceived likelihood of unwanted/beneficial actions, decreased emotional struggle and emotional intensity, and decreased/increased cognitive endorsement of self-limiting/self-efficacious beliefs (Paired Samples Wilcoxon Test average effect size = 0.71, range = [.26, .87], all p<0.008). These results provide an important proof-of-concept for the app. A subsequent study will test the app's effectiveness for at least two weeks using event-contingent reporting for participants' real-life regulatory challenges and ERMS training in context.

For computationally limited agents such as humans, perfectly rational decision-making is almost always out of reach. Instead, people may rely on computationally frugal heuristics that usually yield good outcomes. Although previous research has identified many such heuristics, discovering good heuristics and predicting when they will be used remains challenging. Here, we present a machine learning method that identifies the best heuristics to use in any given situation. To demonstrate the generalizability and accuracy of our method, we compare the strategies it discovers against those used by people across a wide range of multi-alternative risky choice environments in a behavioral experiment that is an order of magnitude larger than any previous experiments of its type. Our method rediscovered known heuristics, identifying them as rational strategies for specific environments, and discovered novel heuristics that had been previously overlooked. Our results show that people adapt their decision strategies to the structure of the environment and generally make good use of their limited cognitive resources, although they tend to collect too little information and their strategy choices do not always fully exploit the structure of the environment.

The purpose of the present studies was to identify an effective tool for helping people to select virtuous life goals that promote their own well-being and contribute to the well-being of others (well-doing). Across two studies, we tested four candidate interventions against each other and a control condition. In the first study (N = 218), the intervention conditions were the eulogy and valued living questionnaire exercises from the Acceptance and Commitment Therapy literature. In the second study (N = 537), the intervention conditions were self-affirmation and value self-confrontation from the social psychology literature and the eulogy exercise. The eulogy exercise is a very brief reflection (3-5 minutes) on how one would like to be remembered by friends and family speaking at one’s funeral. The valued living questionnaire exercise involves rating 10 life domains for importance and behavioral consistency with that importance and reflecting on discrepancies. Self-affirmation involves writing about a time when one acted in line with one’s values. And value self-confrontation involves inducing a discrepancy between participants’ values and those of a socially desirable group. Participants were randomly assigned to one of these brief interventions or a control condition. They were then asked to select a life goal that they would like to start pursuing or make more progress on in the near future. In Study 1, selection was open-ended and participants indicated which of 5 life domains it best fit, including interpersonal goals. In Study 2, the goal was selected from a list of prosocial, personal growth, or materialistic life goals. Across both studies, we found that the eulogy exercise stood out as an effective intervention for helping people select life goals that are likely to promote well-being and well-doing, such as wanting to improve other people’s lives, and avoid life goals that are associated with vices, such as wanting to have many expensive possessions. These findings point to the usefulness of humanistic-existential approaches for promoting character development via life goals and provide an example of how philosophically-informed psychological interventions can be effective.