Related papers: Rationality is Self-Defeating in Permissionless Sy…
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with…
A crucial task for secure communication networks is to determine the minimum of physical requirements to certify a cryptographic protocol. A widely accepted candidate for certification is the principle of relativistic causality which is…
Legislation and public sentiment throughout the world have promoted fairness metrics, explainability, and interpretability as prescriptions for the responsible development of ethical artificial intelligence systems. Despite the importance…
An inductive logic can be formulated in which the elements are not propositions or probability distributions, but information systems. The logic is complete for information systems with binary hypotheses, i.e., it applies to all such…
Recent large-scale events like election fraud and financial scams have shown how harmful coordinated efforts by human groups can be. With the rise of autonomous AI systems, there is growing concern that AI-driven groups could also cause…
A simple framework for reasoning under uncertainty and intervention is introduced. This is achieved in three steps. First, logic is restated in set-theoretic terms to obtain a framework for reasoning under certainty. Second, this framework…
As human science pushes the boundaries towards the development of artificial intelligence (AI), the sweep of progress has caused scholars and policymakers alike to question the legality of applying or utilising AI in various human…
Causality is an important concept both for proving impossibility results and for synthesizing efficient protocols in distributed computing. For asynchronous agents communicating over unreliable channels, causality is well studied and…
In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…
The concept of intelligent software is flawed. The behaviour of software is determined by the hardware that "interprets" it. This undermines claims regarding the behaviour of theorised, software superintelligence. Here we characterise this…
Bounded rationality, that is, decision-making and planning under resource limitations, is widely regarded as an important open problem in artificial intelligence, reinforcement learning, computational neuroscience and economics. This paper…
Many studies have shown that humans are "predictably irrational": they do not act in a fully rational way, but their deviations from rational behavior are quite systematic. Our goal is to see the extent to which we can explain and justify…
Value independence is enormously beneficial for reasoning about software systems at scale. These benefits carry over into the world of formal verification. Reasoning about programs algebraically is a simple affair in a proof assistant,…
I distinguish between pure self-locating credences and superficially self-locating credences, and argue that there is never any rationally compelling way to assign pure self-locating credences. I first argue that from a practical point of…
The classical view of epistemic logic is that an agent knows all the logical consequences of their knowledge base. This assumption of logical omniscience is often unrealistic and makes reasoning computationally intractable. One approach to…
Two natural strategy elimination procedures have been studied for strategic games. The first one involves the notion of (strict, weak, etc) dominance and the second the notion of rationalizability. In the case of dominance the criterion of…
We observe that MLRMs oriented toward human-centric service are highly susceptible to user emotional cues during the deep-thinking stage, often overriding safety protocols or built-in safety checks under high emotional intensity. Inspired…
In experimental applications of bounded-reasoning models, behavior is often summarized by distributions of "levels". We argue that such summaries conflate two conceptually distinct dimensions: a player's type, capturing beliefs about what…
Explanations for artificial intelligence (AI) systems are intended to support the people who are impacted by AI systems in high-stakes decision-making environments, such as doctors, patients, teachers, students, housing applicants, and many…
Accurately modeling human decision-making in security is critical to thinking about when, why, and how to recommend that users adopt certain secure behaviors. In this work, we conduct behavioral economics experiments to model the…