Related papers: Measuring Difficulty of Novelty Reaction
Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a result. This raises a challenging research question: How can…
Current approaches to novelty or anomaly detection are based on deep neural networks. Despite their effectiveness, neural networks are also vulnerable to imperceptible deformations of the input data. This is a serious issue in critical…
Decision support systems enhanced by Artificial Intelligence (AI) are increasingly being used in high-stakes scenarios where errors or biased outcomes can have significant consequences. In this work, we explore the conditions under which…
A critical factor in utilizing agents with Artificial Intelligence (AI) is their robustness to novelty. AI agents include models that are either engineered or trained. Engineered models include knowledge of those aspects of the environment…
Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable…
In most real-world settings, due to limited time or other resources, an agent cannot perform all potentially useful deliberation and information gathering actions. This leads to the metareasoning problem of selecting such actions.…
Today, available methods that assess AI systems are focused on using empirical techniques to measure the performance of algorithms in some specific tasks (e.g., playing chess, solving mazes or land a helicopter). However, these methods are…
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…
We introduce the term Super-Reactive Systems to refer to reactive systems whose construction and behavior are complex, constantly changing and evolving, and heavily interwoven with other systems and the physical world. Finding hidden faults…
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…
Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement…
With increasing ubiquity of artificial intelligence (AI) in modern societies, individual countries and the international community are working hard to create an innovation-friendly, yet safe, regulatory environment. Adequate regulation is…
Artificial Intelligence (AI) systems planned for deployment in real-world applications frequently are researched and developed in closed simulation environments where all variables are controlled and known to the simulator or labeled…
As AI systems become prevalent in high stakes domains such as surveillance and healthcare, researchers now examine how to design and implement them in a safe manner. However, the potential harms caused by systems to stakeholders in complex…
AI has been dealing with uncertainty to have highly accurate results. This becomes even worse with reasonably small data sets or a variation in the data sets. This has far-reaching effects on decision-making, forecasting and learning…
The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task. With the increasing interest in AI scientists and AI involvement in scientific idea generation and paper writing, it also…
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…
We study how people trade off accuracy when using AI-powered tools in professional versus personal contexts for adoption purposes, the determinants of those trade-offs, and how users cope when AI/apps are unavailable. Because modern AI…
A general notion of information-related complexity applicable to both natural and man-made systems is proposed. The overall approach is to explicitly consider a rational agent performing a certain task with a quantifiable degree of success.…
In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead…