相关论文: An AGI with Time-Inconsistent Preferences
A possibly immortal agent tries to maximise its summed discounted rewards over time, where discounting is used to avoid infinite utilities and encourage the agent to value current rewards more than future ones. Some commonly used discount…
There is a consensus that human and non-human subjects experience temporal distortions in many stages of their perceptual and decision-making systems. Similarly, intertemporal choice research has shown that decision-makers undervalue future…
Time-inconsistency is a characteristic of human behavior in which people plan for long-term benefits but take actions that differ from the plan due to conflicts with short-term benefits. Such time-inconsistent behavior is believed to be…
In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities across many critical domains. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict…
For optimal stopping problems with time-inconsistent preference, we measure the inherent level of time-inconsistency by taking the time needed to turn the naive strategies into the sophisticated ones. In particular, when in a repeated…
Understanding how people actually trade off time for money is perhaps the major question in the field of time discounting. There is indeed a vast body of work devoted to explore the underlying mechanisms of the individual decision making…
Time inconsistency is prevalent in dynamic choice problems: a plan of actions to be taken in the future that is optimal for an agent today may not be optimal for the same agent in the future. If the agent is aware of this intra-personal…
An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail. Such an AGI would necessarily have…
Artificial General Intelligence (AGI) may face a confrontation question: under what conditions would a rationally self-interested AGI choose to seize power or eliminate human control (a confrontation) rather than remain cooperative? We…
Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some agents that…
As AI agents become more autonomous, properly aligning their objectives with human preferences becomes increasingly important. We study how effectively an AI agent learns a human principal's preference in choice under risk via stated versus…
This paper proposes a model of choice via agentic artificial intelligence (AI). A key feature is that the AI may misinterpret a menu before recommending what to choose. A single acyclicity condition guarantees that there is a monotonic…
The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…
The following briefly discusses possible difficulties in communication with and control of an AGI (artificial general intelligence), building upon an explanation of The Fermi Paradox and preceding work on symbol emergence and artificial…
Artificial general intelligence (AGI) does not yet exist, but given the pace of technological development in artificial intelligence, it is projected to reach human-level intelligence within roughly the next two decades. After that, many…
A traditional approach to assessing emerging intelligence in the theory of intelligent systems is based on the similarity, "imitation" of human-like actions and behaviors, benchmarking the performance of intelligent systems on the scale of…
The AI research community plays a vital role in shaping the scientific, engineering, and societal goals of AI research. In this position paper, we argue that focusing on the highly contested topic of `artificial general intelligence'…
This paper studies relations among axioms on individuals' intertemporal choices under risk. The focus is on Risk Averse over Time Lotteries (RATL), meaning that a fixed prize is preferred to a lottery with the same monetary prize but a…
An important use of machine learning is to learn what people value. What posts or photos should a user be shown? Which jobs or activities would a person find rewarding? In each case, observations of people's past choices can inform our…
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…