相关论文: An AGI with Time-Inconsistent Preferences

Privacy concerns significantly impact AI adoption, yet little is known about how information environments shape user responses to data leak threats. We conducted a 2 x 3 between-subjects experiment (N=610) examining how risk versus…

Here we examine the paperclip apocalypse concern for artificial general intelligence (or AGI) whereby a superintelligent AI with a simple goal (ie., producing paperclips) accumulates power so that all resources are devoted towards that…

The endeavor of artificial intelligence (AI) is to design autonomous agents capable of achieving complex tasks. Namely, reinforcement learning (RL) proposes a theoretical background to learn optimal behaviors. In practice, RL algorithms…

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…

We study the problem of online learning in two-sided non-stationary matching markets, where the objective is to converge to a stable match. In particular, we consider the setting where one side of the market, the arms, has fixed known set…

Animals and humans make decisions based on their expected outcomes. Since relevant outcomes are often delayed, perceiving delays and choosing between earlier versus later rewards (intertemporal decision-making) is an essential component of…

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is sufficient to achieve Artificial General Intelligence. Instead, we identify Agentic AI as a necessary paradigm for mastering…

The trajectory of intelligence evolution is often framed around the emergence of artificial general intelligence (AGI) and its alignment with human values. This paper challenges that framing by introducing the concept of intelligence…

In recent years prominent intellectuals have raised ethical concerns about the consequences of artificial intelligence. One concern is that an autonomous agent might modify itself to become "superintelligent" and, in supremely effective…

We study whether language models (LMs) exhibit future- versus present-oriented preferences in intertemporal choice and whether those preferences can be systematically manipulated. Using adapted human experimental protocols, we evaluate…

Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what…

Time-inconsistent preferences, where agents favor smaller-sooner over larger-later rewards, are a key feature of human and animal decision-making. Quasi-Hyperbolic (QH) discounting provides a simple yet powerful model for this behavior, but…

Model checking of strategic abilities is a notoriously hard problem, even more so in the realistic case of agents with imperfect information. Assume-guarantee reasoning can be of great help here, providing a way to decompose the complex…

Hadfield-Menell et al. (2017) propose the Off-Switch Game, a model of Human-AI cooperation in which AI agents always defer to humans because they are uncertain about our preferences. I explain two reasons why AI agents might not defer.…

A striking limitation of human cognition is our inability to execute some tasks simultaneously. Recent work suggests that such limitations can arise from a fundamental tradeoff in network architectures that is driven by the sharing of…

Traditionally, AI has been modeled within economics as a technology that impacts payoffs by reducing costs or refining information for human agents. Our position is that, in light of recent advances in generative AI, it is increasingly…

With this paper, we aim to put an issue on the agenda of AI ethics that in our view is overlooked in the current discourse. The current discussions are dominated by topics suchas trustworthiness and bias, whereas the issue we like to…

Feedback from artificial intelligence (AI) is increasingly easy to access and research has already established that people learn from it. But individuals choose when and how to seek such feedback, and more engaged and motivated individuals…

Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement learning, option models (Sutton, Precup \& Singh, 1999; Precup, 2000) provide the framework for this…