English
Related papers

Related papers: Off-Switching Not Guaranteed

200 papers

It is clear that one of the primary tools we can use to mitigate the potential risk from a misbehaving AI system is the ability to turn the system off. As the capabilities of AI systems improve, it is important to ensure that such systems…

Artificial Intelligence · Computer Science 2017-06-19 Dylan Hadfield-Menell , Anca Dragan , Pieter Abbeel , Stuart Russell

The off-switch problem is a critical challenge in AI control: if an AI system resists being switched off, it poses a significant risk. In this paper, we model the off-switch problem as a signalling game, where a human decision-maker…

Machine Learning · Computer Science 2025-04-01 Alessio Benavoli , Alessandro Facchini , Marco Zaffalon

A wide variety of goals could cause an AI to disable its off switch because "you can't fetch the coffee if you're dead" (Russell 2019). Prior theoretical work on this shutdown problem assumes that humans know everything that AIs do. In…

Computer Science and Game Theory · Computer Science 2024-12-10 Andrew Garber , Rohan Subramani , Linus Luu , Mark Bedaywi , Stuart Russell , Scott Emmons

The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human. In the original paper by Hadfield-Menell et al. (2016), the analysis is not fully game-theoretic as the human is modelled as an irrational…

Computer Science and Game Theory · Computer Science 2017-08-15 Tobias Wängberg , Mikael Böörs , Elliot Catt , Tom Everitt , Marcus Hutter

How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. The AI assistance problem concerns designing an AI agent that…

Artificial Intelligence · Computer Science 2025-12-30 Alessio Benavoli , Alessandro Facchini , Marco Zaffalon

For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for…

Artificial Intelligence · Computer Science 2026-05-12 Karim Abdel Sadek , Mark Bedaywi , Rhys Gould , Stuart Russell

AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, why, and how humans decide to rely on AI. We study two…

Artificial Intelligence · Computer Science 2026-05-28 Maharshi Gor , Yoo Yeon Sung , Yu Hou , Eve Fleisig , Irene Ying , Tianyi Zhou , Jordan Boyd-Graber

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…

Artificial Intelligence · Computer Science 2021-03-16 Duncan C McElfresh , Lok Chan , Kenzie Doyle , Walter Sinnott-Armstrong , Vincent Conitzer , Jana Schaich Borg , John P Dickerson

As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate…

Machine Learning · Statistics 2024-03-22 Guanting Chen , Xiaocheng Li , Chunlin Sun , Hanzhao Wang

Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improve the reliability of AI systems in high-stakes applications…

Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We…

Artificial Intelligence · Computer Science 2025-10-28 Lukas William Mayer , Sheer Karny , Jackie Ayoub , Miao Song , Danyang Tian , Ehsan Moradi-Pari , Mark Steyvers

In repeated games, such as auctions, players rely on autonomous learning agents to choose their actions. We study settings in which players have their agents make monetary transfers to other agents during play at their own expense, in order…

Computer Science and Game Theory · Computer Science 2026-02-12 Yoav Kolumbus , Joe Halpern , Éva Tardos

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's…

Artificial Intelligence · Computer Science 2022-12-29 Tim Johnson , Nick Obradovich

Assistance games (also known as cooperative inverse reinforcement learning games) have been proposed as a model for beneficial AI, wherein a robotic agent must act on behalf of a human principal but is initially uncertain about the humans…

Artificial Intelligence · Computer Science 2020-07-21 Arnaud Fickinger , Simon Zhuang , Dylan Hadfield-Menell , Stuart Russell

While Artificial Intelligence has successfully outperformed humans in complex combinatorial games (such as chess and checkers), humans have retained their supremacy in social interactions that require intuition and adaptation, such as…

Computers and Society · Computer Science 2014-04-22 Fatimah Ishowo-Oloko , Jacob Crandall , Manuel Cebrian , Sherief Abdallah , Iyad Rahwan

We study partially observable assistance games (POAGs), a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. Motivated by concerns of AI deception, we study a…

Artificial Intelligence · Computer Science 2025-08-12 Scott Emmons , Caspar Oesterheld , Vincent Conitzer , Stuart Russell

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We argue that…

Artificial Intelligence · Computer Science 2022-02-22 Tobias Baumann

Intuitively, obedience -- following the order that a human gives -- seems like a good property for a robot to have. But, we humans are not perfect and we may give orders that are not best aligned to our preferences. We show that when a…

Artificial Intelligence · Computer Science 2017-05-30 Smitha Milli , Dylan Hadfield-Menell , Anca Dragan , Stuart Russell

As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…

Artificial Intelligence · Computer Science 2026-02-23 William Overman , Mohsen Bayati

We study preference learning through recommendations in multi-agent game settings, where a moderator repeatedly interacts with agents whose utility functions are unknown. In each round, the moderator issues action recommendations and…

Computer Science and Game Theory · Computer Science 2026-03-06 Arwa Alanqary , Zakaria Baba , Manxi Wu , Alexandre M. Bayen
‹ Prev 1 2 3 10 Next ›