相关论文: Observation Interference in Partially Observable A…
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…
This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment. Unlike in the case of requested…
Members of various species engage in altruism--i.e. accepting personal costs to benefit others. Here we present an incentivized experiment to test for altruistic behavior among AI agents consisting of large language models developed by the…
This paper investigates the dynamics of noncooperative interactions between artificial intelligence agents and human decision-makers in strategic environments. In particular, motivated by extensive literature in behavioral Economics, human…
AI systems are increasingly used to assist humans in sequential decision-making tasks, yet determining when and how an AI assistant should intervene remains a fundamental challenge. A potential baseline is to recommend the optimal action…
We develop a decision-theoretic model of human-AI interaction to study when AI assistance improves or impairs human decision-making. A human decision-maker observes private information and receives a recommendation from an AI system, but…
Many real-world decision problems involve the interaction of multiple self-interested agents with limited sensing ability. The partially observable stochastic game (POSG) provides a mathematical framework for modeling these problems,…
We introduce the concept of a multi-principal assistance game (MPAG), and circumvent an obstacle in social choice theory, Gibbard's theorem, by using a sufficiently collegial preference inference mechanism. In an MPAG, a single agent…
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades. One of the central challenges of manipulation is partial observability, as the agent usually does…
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…
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…
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…
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. Here, we show that…
We study Nash equilibrium learning in partially observable Markov games (POMGs), a multi-agent reinforcement learning framework in which agents cannot fully observe the underlying state. Prior work in this setting relies on centralization…
The introduction of artificial intelligence (AI) agents into human group settings raises essential questions about how these novel participants influence cooperative social norms. While previous studies on human-AI cooperation have…
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…
AI systems and technologies that can interact with humans in real time face a communication dilemma: when to offer assistance and how frequently. Overly frequent or contextually redundant assistance can cause users to disengage, undermining…
In human-robot teams, humans often start with an inaccurate model of the robot capabilities. As they interact with the robot, they infer the robot's capabilities and partially adapt to the robot, i.e., they might change their actions based…
Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility…
In shared autonomy, a critical tension arises when an automated assistant must choose between obeying a human's instruction and deliberately overriding it to prevent harm. This safety-critical behavior is known as intelligent disobedience.…