Related papers: Choice Between Partial Trajectories: Disentangling…

To enable effective human-AI collaboration, merely optimizing AI performance without considering human factors is insufficient. Recent research has shown that designing AI agents that take human behavior into account leads to improved…

Existing observational approaches for learning human preferences, such as inverse reinforcement learning, usually make strong assumptions about the observability of the human's environment. However, in reality, people make many important…

Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put…

Can stated preferences inform counterfactual analyses of actual choice? This research proposes a novel approach to researchers who have access to both stated choices in hypothetical scenarios and actual choices, matched or unmatched. The…

In consequential domains, it is often impossible to compel individuals to take treatment, so that optimal policy rules are merely suggestions in the presence of human non-adherence to treatment recommendations. We study personalized…

Decision-making with information displays is a key focus of research in areas like human-AI collaboration and data visualization. However, what constitutes a decision problem, and what is required for an experiment to conclude that…

An ethical value-action gap exists when there is a discrepancy between intentions and actions. This discrepancy may be caused by social and structural obstacles as well as cognitive biases. Computational models of cognition and affect can…

It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. The types of behavior interpreted as evidence of the reward…

We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us…

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

Building artificial intelligence (AI) that aligns with human values is an unsolved problem. Here, we developed a human-in-the-loop research pipeline called Democratic AI, in which reinforcement learning is used to design a social mechanism…

Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study this question using revealed preference techniques, I…

Bootstrapping large language models (LLMs) through preference-based policy optimization offers a promising direction for aligning model behavior with human preferences without relying on extensive manual annotations. In this work, we…

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function. However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and…

In machine learning, the selection of a promising model from a potentially large number of competing models and the assessment of its generalization performance are critical tasks that need careful consideration. Typically, model selection…

The aim of path planning is to reach the goal from starting point by searching for the route of an agent. In the path planning, the routes may vary depending on the number of variables such that it is important for the agent to reach…

Conventional automated decision-support systems often prioritize predictive accuracy, overlooking the complexities of real-world settings where stakeholders' preferences may diverge or conflict. This can lead to outcomes that disadvantage…

Shared control allows the human driver to collaborate with an assistive driving system while retaining the ability to make decisions and take control if necessary. However, human-vehicle teaming and planning are challenging due to…

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…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…