What are the mechanisms underlying metacognitive learning?

How is it that humans can solve complex planning tasks so efficiently despite limited cognitive resources? One reason is its ability to know how to use its limited computational resources to make clever choices. We postulate that people learn this ability from trial and error (metacognitive reinforcement learning). Here, we systematize models of the underlying learning mechanisms and enhance them with more sophisticated additional mechanisms. We fit the resulting 86 models to human data collected in previous experiments where different phenomena of metacognitive learning were demonstrated and performed Bayesian model selection. Our results suggest that a gradient ascent through the space of cognitive strategies can explain most of the observed qualitative phenomena, and is therefore a promising candidate for explaining the mechanism underlying metacognitive learning.

Leveraging AI to improve human planning in large partially observable environments

AI can not only outperform people in many planning tasks, but also teach them how to plan better. All prior work was conducted in fully observable environments, but the real world is only partially observable. To bridge this gap, we developed the first metareasoning algorithm for discovering resource-rational strategies for human planning in partially observable environments. Moreover, we developed an intelligent tutor teaching the automatically discovered strategy by giving people feedback on how they plan in increasingly more difficult problems. We showed that our strategy discovery method is superior to the state-of-the-art and tested our intelligent tutor in a preregistered training experiment with 330 participants. The experiment showed that people's intuitive strategies for planning in partially observable environments are highly suboptimal, but can be substantially improved by training with our intelligent tutor. This suggests our human-centred tutoring approach can successfully boost human planning in complex, partially observable sequential decision problems.

Toward a normative theory of (self-)management by goal-setting

People are often confronted with problems whose complexity exceeds their cognitive capacities. To deal with this complexity, individuals and managers can break complex problems down into a series of subgoals. Which subgoals are most effective depends on people's cognitive constraints and the cognitive mechanisms of goal pursuit. This creates an untapped opportunity to derive practical recommendations for which subgoals managers and individuals should set from cognitive models of bounded rationality. To seize this opportunity, we apply the principle of resource-rationality to formulate a mathematically precise normative theory of (self-)management by goal-setting. We leverage this theory to computationally derive optimal subgoals from a resource-rational model of human goal pursuit. Finally, we show that the resulting subgoals improve the problem-solving performance of bounded agents and human participants. This constitutes a first step towards grounding prescriptive theories of management and practical recommendations for goal-setting in computational models of the relevant psychological processes and cognitive limitations.

Boosting human decision-making with AI-generated decision aids

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.

Have I done enough planning or should I plan more?

People's decisions about how to allocate their limited computational resources are essential to human intelligence. An important component of this metacognitive ability is deciding whether to continue thinking about what to do and move on to the next decision. Here, we show that people acquire this ability through learning and reverse-engineer the underlying learning mechanisms. Using a process-tracing paradigm that externalises human planning, we find that people quickly adapt how much planning they perform to the cost and benefit of planning. To discover the underlying metacognitive learning mechanisms we augmented a set of reinforcement learning models with metacognitive features and performed Bayesian model selection. Our results suggest that the metacognitive ability to adjust the amount of planning might be learned through a policy-gradient mechanism that is guided by metacognitive pseudo-rewards that communicate the value of planning.

Automatic discovery and description of human planning strategies

Scientific discovery concerns finding patterns in data and creating insightful hypotheses that explain these patterns. Traditionally, this process required human ingenuity, but with the galloping advances in artificial intelligence (AI) it becomes feasible to automate some parts of scientific discovery. In this work we leverage AI for strategy discovery for understanding human planning. In the state-of-the-art methods data about the process of human planning is often used to group similar behaviors together and formulate verbal descriptions of the strategies which might underlie those groups. Here, we automate these two steps. Our algorithm, called Human-Interpret, uses imitation learning to describe process-tracing data collected in psychological experiments with the Mouselab-MDP paradigm in terms of a procedural formula. Then, it translates that formula to natural language using a pre-defined predicate dictionary. We test our method on a benchmark data set that researchers have previously scrutinized manually. We find that the descriptions of human planning strategies obtained automatically are about as understandable as human-generated descriptions. They also cover a substantial proportion of all types of human planning strategies that had been discovered manually. Our method saves scientists' time and effort as all the reasoning about human planning is done automatically. This might make it feasible to more rapidly scale up the search for yet undiscovered cognitive strategies to many new decision environments, populations, tasks, and domains. Given these results, we believe that the presented work may accelerate scientific discovery in psychology, and due to its generality, extend to problems from other fields.

Optimal To-Do List Gamification for Long Term Planning

Most people struggle with prioritizing work. While inexact heuristics have been developed over time, there is still no tractable principled algorithm for deciding which of the many possible tasks one should tackle in any given day, month, week, or year. Additionally, some people suffer from cognitive biases such as the present bias, leading to prioritization of their immediate experience over long-term consequences which manifests itself as procrastination and inefficient task prioritization. Our method utilizes optimal gamification to help people overcome these problems by incentivizing each task by a number of points that convey how valuable it is in the long-run. We extend the previous version of our optimal gamification method with added services for helping people decide which tasks should and should not be done when there is not enough time to do everything. To improve the efficiency and scalability of the to-do list solver, we designed a hierarchical procedure that tackles the problem from the top-level goals to fine-grained tasks. We test the accuracy of the incentivised to-do list by comparing the performance of the strategy with the points computed exactly using Value Iteration for a variety of case studies. These case studies were specifically designed to cover the corner cases to get an accurate judge of performance. Our method yielded the same performance as the exact method for all case studies. To demonstrate its functionality, we released an API that makes it easy to deploy our method in Web and app services. We assessed the scalability of our method by applying it to to-do lists with increasingly larger numbers of goals, sub-goals per goal, hierarchically nested levels of subgoals. We found that the method provided through our API is able to tackle fairly large to-do lists having a 576 tasks. This indicates that our method is suitable for real-world applications.

Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning

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.

Optimal to-do list gamification

What should I work on first? What can wait until later? Which projects should I prioritize and which tasks are not worth my time? These are challenging questions that many people face every day. People's intuitive strategy is to prioritize their immediate experience over the long-term consequences. This leads to procrastination and the neglect of important long-term projects in favor of seemingly urgent tasks that are less important. Optimal gamification strives to help people overcome these problems by incentivizing each task by a number of points that communicates how valuable it is in the long-run. Unfortunately, computing the optimal number of points with standard dynamic programming methods quickly becomes intractable as the number of a person's projects and the number of tasks required by each project increase. Here, we introduce and evaluate a scalable method for identifying which tasks are most important in the long run and incentivizing each task according to its long-term value. Our method makes it possible to create to-do list gamification apps that can handle the size and complexity of people's to-do lists in the real world.

Automatic Discovery of Interpretable Planning Strategies

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors, with decision aids, such as decision trees and flowcharts. Designing effective decision aids is a difficult problem. We propose that recently developed reinforcement learning methods for discovering clever heuristics for good decision-making can be partially leveraged to assist human experts in this design process. One of the biggest remaining obstacles to leveraging the aforementioned methods for improving human decision-making is that the policies they learn are opaque to people. To solve this problem, we introduce AI-Interpret: a general method for transforming idiosyncratic policies into simple and interpretable descriptions. Our algorithm combines recent advances in imitation learning and program induction with a new clustering method for identifying a large subset of demonstrations that can be accurately described by a simple, high-performing decision rule. We evaluate our new AI-Interpret algorithm and employ it to translate information-acquisition policies discovered through metalevel reinforcement learning. The results of three large behavioral experiments showed that the provision of decision rules as flowcharts significantly improved people's planning strategies and decisions across three different classes of sequential decision problems. Furthermore, a series of ablation studies confirmed that our AI-Interpret algorithm was critical to the discovery of interpretable decision rules and that it is ready to be applied to other reinforcement learning problems. We conclude that the methods and findings presented in this article are an important step towards leveraging automatic strategy discovery to improve human decision-making.