Search for: All records

AI decision-support tools typically offer a fixed type of assistance, like AI recommendations and explanations, regardless of the specific decision, individual, or broader context. This fixed design has been shown to hinder both human-AI decision accuracy and human skill improvement in the task. We posit that AI assistance needs to be dynamic, changing in response to contextual factors (e.g., AI uncertainty, task difficulty), individual differences, and specified objectives (e.g., decision accuracy, skill improvement). To enable such adaptive support, we propose reinforcement learning (RL) as a general approach for modeling human-AI decision-making to optimize human-AI interaction for diverse objectives. RL enables optimizing various objectives in AI-assisted decision-making by tailoring and adaptively providing decision support to humans --- the right type of assistance, to the right person, at the right time. We instantiated our approach with two objectives: human-AI accuracy on the decision-making task and human skill improvement (i.e., learning about the task) and learned decision support policies from previous human-AI interaction data. We compared the optimized policies against several baselines in AI-assisted decision-making. Across two experiments (N = 316 and N = 964), our results consistently demonstrated that people interacting with policies optimized for accuracy achieve significantly higher accuracy --- and even human-AI complementarity --- compared to those interacting with any other type of AI support. Our results further indicated that human learning was more difficult to optimize than accuracy. While the policies learned the best available actions to optimize learning, participants who interacted with learning-optimized policies showed significant learning improvement only at times. Our research (1) demonstrates offline RL to be a promising approach to model the dynamics of human-AI decision-making, leading to policies that may optimize various objectives and provide novel insights about the AI-assisted decision-making space, and (2) emphasizes the importance of considering skill improvement and other human-centric objectives beyond accuracy in AI-assisted decision-making, opening up the novel research challenge of optimizing human-AI interaction for such objectives. 

In settings where an AI agent nudges a human agent toward a goal, the AI can quickly learn a high-quality policy by modeling the human well. Despite behavioral evidence that humans hyperbolically discount future rewards, we model human as Markov Decision Processes (MDPs) with exponential discounting. This is because planning is difficult with non-exponential discounts. In this work, we investigate whether the performance benefits of modeling humans as hyperbolic discounters outweigh the computational costs. We focus on AI interventions that change the human's discounting (i.e. decreases the human's "nearsightedness" to help them toward distant goals). We derive a fixed exponential discount factor that can approximate hyperbolic discounting, and prove that this approximation guarantees the AI will never miss a necessary intervention. We also prove that our approximation causes fewer false positives (unnecessary interventions) than the mean hazard rate, another well-known method for approximating hyperbolic MDPs as exponential ones. Surprisingly, our experiments demonstrate that exponential approximations outperform hyperbolic ones in online learning, even when the ground-truth human MDP is hyperbolically discounted. 

Just-in-Time Adaptive Interventions (JITAIs) are a class of personalized health interventions developed within the behavioral science community. JITAIs aim to provide the right type and amount of support by iteratively selecting a sequence of intervention options from a pre-defined set of components in response to each individual's time varying state. In this work, we explore the application of reinforcement learning methods to the problem of learning intervention option selection policies. We study the effect of context inference error and partial observability on the ability to learn effective policies. Our results show that the propagation of uncertainty from context inferences is critical to improving intervention efficacy as context uncertainty increases, while policy gradient algorithms can provide remarkable robustness to partially observed behavioral state information. 

Abstract Maternal educational attainment (MEA) shapes offspring health through multiple potential pathways. Differential DNA methylation may provide a mechanistic understanding of these long-term associations. We aimed to quantify the associations of MEA with offspring DNA methylation levels at birth, in childhood and in adolescence. Using 37 studies from high-income countries, we performed meta-analysis of epigenome-wide association studies (EWAS) to quantify the associations of completed years of MEA at the time of pregnancy with offspring DNA methylation levels at birth (n = 9 881), in childhood (n = 2 017), and adolescence (n = 2 740), adjusting for relevant covariates. MEA was found to be associated with DNA methylation at 473 cytosine-phosphate-guanine sites at birth, one in childhood, and four in adolescence. We observed enrichment for findings from previous EWAS on maternal folate, vitamin-B₁₂concentrations, maternal smoking, and pre-pregnancy BMI. The associations were directionally consistent with MEA being inversely associated with behaviours including smoking and BMI. Our findings form a bridge between socio-economic factors and biology and highlight potential pathways underlying effects of maternal education. The results broaden our understanding of bio-social associations linked to differential DNA methylation in multiple early stages of life. The data generated also offers an important resource to help a more precise understanding of the social determinants of health.