Type 1 Diabetes (T1D) management requires continuous adjustment of insulin and lifestyle behaviors to maintain blood glucose within a safe target range. Although automated insulin delivery (AID) systems have improved glycemic outcomes, many patients still fail to achieve recommended clinical targets, warranting new approaches to improve glucose control in patients with T1D. While reinforcement learning (RL) has been utilized as a promising approach, current RL-based methods focus primarily on insulin-only treatment and do not provide behavioral recommendations for glucose control. To address this gap, we propose GUIDE, an RL-based decision-support framework designed to complement AID technologies by providing behavioral recommendations to prevent abnormal glucose events. GUIDE generates structured actions defined by intervention type, magnitude, and timing, including bolus insulin administration and carbohydrate intake events. GUIDE integrates a patient-specific glucose level predictor trained on real-world continuous glucose monitoring data and supports both offline and online RL algorithms within a unified environment. We evaluate both off-policy and on-policy methods across 25 individuals with T1D using standardized glycemic metrics. Among the evaluated approaches, the CQL-BC algorithm demonstrates the highest average time-in-range, reaching 85.49

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications, challenging agents with managing risks encompassing the misuse and negative side effects. These tasks include tests to evaluate the safety of agents in daily scenarios as well as their robustness against indirect prompt injection attacks. Our experiments demonstrate that baseline agents, based on state-of-the-art LLMs, often fail to effectively prevent harm while performing the tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments.

Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions.

Amid the growing prevalence of human – AI interaction, large language models and other AI-based entities increasingly provide forms of companionship to human users. Such AI companionship – i.e., bonded relationships between humans and AI systems that resemble the relationships people have with family members, friends, and romantic partners – might substantially benefit humans. Yet such relationships can also do profound harm. We propose a framework for analyzing potential negative impacts of AI companionship by identifying specific harmful traits of AI companions and speculatively mapping causal pathways back from these traits to possible causes and forward to potential harmful effects. We provide detailed, structured analysis of four potentially harmful traits – the absence of natural endpoints for relationships, vulnerability to product sunsetting, high attachment anxiety, and propensity to engender protectiveness – and briefly discuss fourteen others. For each trait, we propose hypotheses connecting causes – such as misaligned optimization objectives and the digital nature of AI companions – to fundamental harms – including reduced autonomy, diminished quality of human relationships, and deception. Each hypothesized causal connection identifies a target for potential empirical evaluation. Our analysis examines harms at three levels: to human partners directly, to their relationships with other humans, and to society broadly. We examine how existing law struggles to address these emerging harms, discuss potential benefits of AI companions, and conclude with design recommendations for mitigating risks. This analysis offers immediate suggestions for reducing risks while laying a foundation for deeper investigation of this critical but understudied topic.

Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly describes how humans generate preferences risks learning a poor approximation of the human's reward function. In this paper, we conduct three human studies to asses whether one can influence the expression of real human preferences to more closely conform to a desired preference model. Importantly, our approach does not seek to alter the human's unobserved reward function. Rather, we change how humans use this reward function to generate preferences, such that they better match whatever preference model is assumed by a particular RLHF algorithm. We introduce three interventions: showing humans the quantities that underlie a preference model, which is normally unobservable information derived from the reward function; training people to follow a specific preference model; and modifying the preference elicitation question. All intervention types show significant effects, providing practical tools to improve preference data quality and the resultant alignment of the learned reward functions. Overall we establish a novel research direction in model alignment: designing interfaces and training interventions to increase human conformance with the modeling assumptions of the algorithm that will learn from their input.

When users are dissatisfied with recommendations from a recommender system, they often lack fine-grained controls for changing them. Large language models (LLMs) offer a solution by allowing users to guide their recommendations through natural language requests (e.g., "I want to see respectful posts with a different perspective than mine"). We propose a method, CTRL-Rec, that allows for natural language control of traditional recommender systems in real-time with computational efficiency. Specifically, at training time, we use an LLM to simulate whether users would approve of items based on their language requests, and we train embedding models that approximate such simulated judgments. We then integrate these user-request-based predictions into the standard weighting of signals that traditional recommender systems optimize. At deployment time, we require only a single LLM embedding computation per user request, allowing for real-time control of recommendations. In experiments with the MovieLens dataset, our method consistently allows for fine-grained control across a diversity of requests. In a study with 19 Letterboxd users, we find that CTRL-Rec was positively received by users and significantly enhanced users' sense of control and satisfaction with recommendations compared to traditional controls.

Large language models (LLMs) must often respond to highly ambiguous user requests. In such cases, the LLM's best response may be to ask a clarifying question to elicit more information. Existing LLMs often respond by presupposing a single interpretation of such ambiguous requests, frustrating users who intended a different interpretation. We speculate this is caused by current preference data labeling practice, where LLM responses are evaluated only on their prior contexts. To address this, we assign preference labels by simulating their expected outcomes in future turns. This allows LLMs to learn to ask clarifying questions when it can generate responses that are tailored to each user interpretation in future turns. On open-domain QA datasets with multiple annotations, we evaluate systems based on their ability to ask clarifying questions to recover each user's interpretation and expected answer. We compare systems trained using our proposed preference labeling methods against standard methods, which assign preferences based on only prior context. Our method achieves a 5% improvement in F1 measured against the answer set from different interpretations of each query, showing the value of modeling future conversation turns. We further demonstrate that our method can be used to train models to judiciously determine when to ask clarifying questions, directly answering the question when clarification is unnecessary. In our experiments, we find that our method achives a 3% improvement in accuracy of such judgments over existing methods.

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in practice, designing rewards is difficult, and even when specified, evaluating their correctness is equally problematic: how do we know if a reward function is correctly specified? In our work, we address these challenges by focusing on reward alignment – assessing whether a reward function accurately encodes the preferences of a human stakeholder. As a concrete measure of reward alignment, we introduce the Trajectory Alignment Coefficient to quantify the similarity between a human stakeholder's ranking of trajectory distributions and those induced by a given reward function. We show that the Trajectory Alignment Coefficient exhibits desirable properties, such as not requiring access to a ground truth reward, invariance to potential-based reward shaping, and applicability to online RL. Additionally, in an 11 – person user study of RL practitioners, we found that access to the Trajectory Alignment Coefficient during reward selection led to statistically significant improvements. Compared to relying only on reward functions, our metric reduced cognitive workload by 1.5x, was preferred by 82

Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent – and resulting preferences – for humans to have? We propose a new preference model that incorporates human beliefs and provide a normative theory that bounds the error on the final learned policy based on the mismatch between the human's beliefs and an idealized set of beliefs. We then confirm via a human study that beliefs about agent capabilities do, in fact, significantly affect preferences and can be influenced through simple interventions. Additionally, we empirically show through synthetic experiments that it is often suboptimal for human preference labelers to assume agent optimality. Collectively, these results theoretically and empirically demonstrate how reducing the mismatch between human beliefs and agent capabilities can lead to more performant RLHF and point toward new best practices for RLHF practitioners.

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the model by optimizing the learned reward via reinforcement learning (RL). This paradigm assumes that human preferences are distributed according to reward, but recent work suggests that they instead follow the regret under the user's optimal policy. Thus, learning a reward function from feedback is not only based on a flawed assumption of human preference, but also leads to unwieldy optimization challenges that stem from policy gradients or bootstrapping in the RL phase. Because of these optimization challenges, contemporary RLHF methods restrict themselves to contextual bandit settings (e.g., as in large language models) or limit observation dimensionality (e.g., state-based robotics). We overcome these limitations by introducing a new family of algorithms for optimizing behavior from human feedback using the regret-based model of human preferences. Using the principle of maximum entropy, we derive Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions, circumventing the need for RL. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs. This enables CPL to elegantly scale to high-dimensional and sequential RLHF problems while being simpler than prior methods.

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return. Recent work casts doubt on the validity of this assumption, proposing an alternative preference model based upon regret. We investigate the consequences of assuming preferences are based upon partial return when they actually arise from regret. We argue that the learned function is an approximation of the optimal advantage function, not a reward function. We find that if a specific pitfall is addressed, this incorrect assumption is not particularly harmful, resulting in a highly shaped reward function. Nonetheless, this incorrect usage of the approximation of the optimal advantage function is less desirable than the appropriate and simpler approach of greedy maximization of it. From the perspective of the regret preference model, we also provide a clearer interpretation of fine tuning contemporary large language models with RLHF. This paper overall provides insight regarding why learning under the partial return preference model tends to work so well in practice, despite it conforming poorly to how humans give preferences.

Reinforcement Learning from Human Feedback (RLHF)has been crucial to the recent success of Large Language Models (LLMs), however it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represent human preferences, which is in turn used by an online reinforcement learning (RL) algorithm to optimized the LLM. A prominent issue with such methods is reward over-optimization or reward hacking, where the performance as measured by the learned proxy reward model increases, but the true model quality plateaus or even deteriorates. Direct Alignment Algorithms (DDAs), such as Direct Preference Optimization (DPO) have emerged as alternatives to the classical RLHF pipeline. However, despite not training a separate proxy reward model or using RL, they still commonly deteriorate from over-optimization. While the so-called reward hacking phenomenon is not well-defined for DAAs, we still uncover similar trends: at higher KL-budgets, DAA algorithms exhibit similar degradation patters to their classic RLHF counterparts. In particular, we find that DAA methods deteriorate not only across a wide range of KL-budgets, but also often before even a single epoch of the dataset is completed. Through extensive empirical experimentation this work formulates the reward over-optimization or hacking problem for DAAs and explores its consequences across objectives, training regimes, and model scales.

This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaws in reward functions. We survey research that is published in top-tier venues and focuses on reinforcement learning (RL) for autonomous driving (AD). Specifically, we closely examine the reported reward function in each publication and present these reward functions in a complete and standardized format in the appendix. Wherever we have sufficient information, we apply the 8 sanity checks to each surveyed reward function, revealing near-universal flaws in reward design for AD that might also exist pervasively across reward design for other tasks. Lastly, we explore promising directions that may aid the design of reward functions for AD in subsequent research, following a process of inquiry that can be adapted to other domains.

In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often necessarily sparse. For example, a true task metric might encode a reward of 1 upon success and 0 otherwise. The sparsity of these true task metrics can make them hard to learn from, so in practice they are often replaced with alternative dense reward functions. These dense reward functions are typically designed by experts through an ad hoc process of trial and error. In this process, experts manually search for a reward function that improves performance with respect to the task metric while also enabling an RL algorithm to learn faster. This process raises the question of whether the same reward function is optimal for all algorithms, i.e., whether the reward function can be overfit to a particular algorithm. In this paper, we study the consequences of this wide yet unexamined practice of trial-and-error reward design. We first conduct computational experiments that confirm that reward functions can be overfit to learning algorithms and their hyperparameters. We then conduct a controlled observation study which emulates expert practitioners' typical experiences of reward design, in which we similarly find evidence of reward function overfitting. We also find that experts' typical approach to reward design---of adopting a myopic strategy and weighing the relative goodness of each state-action pair---leads to misdesign through invalid task specifications, since RL algorithms use cumulative reward rather than rewards for individual state-action pairs as an optimization target. Code, data: github.com/serenabooth/reward-design-perils

The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the reward function from human-generated preferences between pairs of trajectory segments, a type of reinforcement learning from human feedback (RLHF). These human preferences are typically assumed to be informed solely by partial return, the sum of rewards along each segment. We find this assumption to be flawed and propose modeling human preferences instead as informed by each segment's regret, a measure of a segment's deviation from optimal decision-making. Given infinitely many preferences generated according to regret, we prove that we can identify a reward function equivalent to the reward function that generated those preferences, and we prove that the previous partial return model lacks this identifiability property in multiple contexts. We empirically show that our proposed regret preference model outperforms the partial return preference model with finite training data in otherwise the same setting. Additionally, we find that our proposed regret preference model better predicts real human preferences and also learns reward functions from these preferences that lead to policies that are better human-aligned. Overall, this work establishes that the choice of preference model is impactful, and our proposed regret preference model provides an improvement upon a core assumption of recent research. We have open sourced our experimental code, the human preferences dataset we gathered, and our training and preference elicitation interfaces for gathering a such a dataset.

This paper describes design principles and a system, based on reinforcement learning and procedural animation, to create an autonomous character capable of believable acting—exhibiting a responsive and expressive illusion of interactive life, grounded in its subjective experience of its world. The design principles incorporate knowledge from animation, human-computer interaction, and psychology, articulating guidelines that, when followed, support a viewer’s suspension of disbelief. The system’s reinforcement learning brain generates action, emotion, and attention signals based on motivational drives, and its procedural animation system translates those signals into expressive biophysical movement in real time. We demonstrate the system on a stylized quadruped character in a virtual habitat. In a user study, participants rated the character favorably on animacy and ability to experience emotions, which is consistent with finding the character believable.

Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. A robot or other agent could leverage an understanding of such implicit human feedback to improve its task performance at no cost to the human. This approach contrasts with common agent teaching methods based on demonstrations, critiques, or other guidance that need to be attentively and intentionally provided. In this paper, we first define the general problem of learning from implicit human feedback and then propose to address this problem through a novel data-driven framework, EMPATHIC. This two-stage method consists of (1) mapping implicit human feedback to relevant task statistics such as reward, optimality, and advantage; and (2) using such a mapping to learn a task. We instantiate the first stage and three second-stage evaluations of the learned mapping. To do so, we collect a dataset of human facial reactions while participants observe an agent execute a sub-optimal policy for a prescribed training task. We train a deep neural network on this data and demonstrate its ability to (1) infer relative reward ranking of events in the training task from prerecorded human facial reactions; (2) improve the policy of an agent in the training task using live human facial reactions; and (3) transfer to a novel domain in which it evaluates robot manipulation trajectories.

Learning from rewards generated by a human trainer observing an agent in action has been proven to be a powerful method for teaching autonomous agents to perform challenging tasks, especially for those non-technical users. Since the efficacy of this approach depends critically on the reward the trainer provides, we consider how the interaction between the trainer and the agent should be designed so as to increase the efficiency of the training process. This article investigates the influence of the agent's socio-competitive feedback on the human trainer's training behavior and the agent's learning. The results of our user study with 85 participants suggest that the agent's passive socio-competitive feedback—showing performance and score of agents trained by trainers in a leaderboard—substantially increases the engagement of the participants in the game task and improves the agents' performance, even though the participants do not directly play the game but instead train the agent to do so. Moreover, making this feedback active—sending the trainer her agent's performance relative to others—further induces more participants to train agents longer and improves the agent's learning. Our further analysis shows that agents trained by trainers affected by both the passive and active social feedback could obtain a higher performance under a score mechanism that could be optimized from the trainer's perspective and the agent's additional active social feedback can keep participants to further train agents to learn policies that can obtain a higher performance under such a score mechanism.

In this work, we address a relatively unexplored aspect of designing agents that learn from human reward. We investigate how an agent's non-task behavior can affect a human trainer's training and agent learning. We use the TAMER framework, which facilitates the training of agents by human-generated reward signals, i.e., judgements of the quality of the agent's actions, as the foundation for our investigation. Then, starting from the premise that the interaction between the agent and the trainer should be bi-directional, we propose two new training interfaces to increase a human trainer's active involvement in the training process and thereby improve the agent's task performance. One provides information on the agent's uncertainty which is a metric calculated as data coverage, the other on its performance. Our results from a 51-subject user study show that these interfaces can induce the trainers to train longer and give more feedback. The agent's performance, however, increases only in response to the addition of performance-oriented information, not by sharing uncertainty levels. These results suggest that the organizational maxim about human behavior, "you get what you measure"—i.e., sharing metrics with people causes them to focus on optimizing those metrics while de-emphasizing other objectives—also applies to the training of agents. Using principle component analysis, we show how trainers in the two conditions train agents differently. In addition, by simulating the influence of the agent's uncertainty–informative behavior on a human's training behavior, we show that trainers could be distracted by the agent sharing its uncertainty levels about its actions, giving poor feedback for the sake of reducing the agent's uncertainty without improving the agent's performance.