English
Related papers

Related papers: Corrigibility Transformation: Constructing Goals T…

200 papers

Corrigibility is a safety property for artificially intelligent agents. A corrigible agent will not resist attempts by authorized parties to alter the goals and constraints that were encoded in the agent when it was first started. This…

Artificial Intelligence · Computer Science 2020-04-06 Koen Holtman

Corrections offer a natural modality for people to provide feedback to a robot, by (i) intervening in the robot's behavior when they believe the robot is failing (or will fail) the task objectives and (ii) modifying the robot's behavior to…

Robotics · Computer Science 2026-02-24 Anjiabei Wang , Shuangge Wang , Tesca Fitzgerald

How can humans stay in control of advanced artificial intelligence systems? One proposal is corrigibility, which requires the agent to follow the instructions of a human overseer, without inappropriately influencing them. In this paper, we…

Artificial Intelligence · Computer Science 2023-06-01 Ryan Carey , Tom Everitt

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…

Human-Computer Interaction · Computer Science 2019-06-06 Gagan Bansal , Besmira Nushi , Ece Kamar , Dan Weld , Walter Lasecki , Eric Horvitz

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

For effective human-robot collaboration, a robot must align its actions with human goals, even as they change mid-task. Prior approaches often assume fixed goals, reducing goal prediction to a one-time inference. However, in real-world…

Robotics · Computer Science 2025-11-21 Debasmita Ghose , Oz Gitelson , Ryan Jin , Grace Abawe , Marynel Vazquez , Brian Scassellati

If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous benefits. In fully observable environments, most reward…

Artificial Intelligence · Computer Science 2022-10-13 Alexander Matt Turner , Prasad Tadepalli

Corrigibility of autonomous agents is an under explored part of system design, with previous work focusing on single agent systems. It has been suggested that uncertainty over the human preferences acts to keep the agents corrigible, even…

Computer Science and Game Theory · Computer Science 2025-01-10 Edmund Dable-Heath , Boyko Vodenicharski , James Bishop

The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for…

Adaptation and Self-Organizing Systems · Physics 2011-09-06 Wolfgang Konen

Any agent that is part of the environment it interacts with and has versatile actuators (such as arms and fingers), will in principle have the ability to self-modify -- for example by changing its own source code. As we continue to create…

Artificial Intelligence · Computer Science 2016-05-11 Tom Everitt , Daniel Filan , Mayank Daswani , Marcus Hutter

The goal of this research is to develop agents that are adaptive and predictable and timely. At first blush, these three requirements seem contradictory. For example, adaptation risks introducing undesirable side effects, thereby making…

Artificial Intelligence · Computer Science 2011-06-02 D. F. Gordon

Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing such objectives often produces undesirable outcomes; this phenomenon is known as reward hacking. Such outcomes are not necessarily…

Artificial Intelligence · Computer Science 2026-04-27 Henrik Marklund , Alex Infanger , Benjamin Van Roy

Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward…

Artificial Intelligence · Computer Science 2023-04-14 Victoria Krakovna , Janos Kramar

AI systems that model and interact with users can update their models over time to reflect new information and changes in the environment. Although these updates may improve the overall performance of the AI system, they may actually hurt…

Machine Learning · Computer Science 2020-08-20 Jonathan Martinez , Kobi Gal , Ece Kamar , Levi H. S. Lelis

When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop…

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…

Machine Learning · Computer Science 2020-12-17 Li Zhou , Kevin Small

Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding methods for…

Machine Learning · Computer Science 2022-11-21 Frank Röder , Manfred Eppe

Machine learning systems are often used in settings where individuals adapt their features to obtain a desired outcome. In such settings, strategic behavior leads to a sharp loss in model performance in deployment. In this work, we aim to…

Machine Learning · Computer Science 2021-06-11 Yatong Chen , Jialu Wang , Yang Liu

Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created…

Machine Learning · Computer Science 2020-03-11 Johannes Schneider

Serious games are widely used for learning and training across domains such as healthcare, defense, and education. Persistent challenges remain, however, including static scenario design, authoring bottlenecks, limited learner modeling, and…

Artificial Intelligence · Computer Science 2026-05-22 Priyamvada Tripathi , Bill Kapralos
‹ Prev 1 2 3 10 Next ›