Related papers: Probably Approximately Knowing
An implicit expectation of asking users to rate agents, such as an AI decision-aid, is that they will use only relevant information -- ask them about an agent's benevolence, and they should consider whether or not it was kind. Behavioral…
Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost. These approaches, however, lack a probabilistic interpretation. Furthermore, while most probabilistic models to goal…
In situations where explicit communication is limited, human collaborators act by learning to: (i) infer meaning behind their partner's actions, and (ii) convey private information about the state to their partner implicitly through…
In the Bayesian approach to quantum mechanics, probabilities--and thus quantum states--represent an agent's degrees of belief, rather than corresponding to objective properties of physical systems. In this paper we investigate the concept…
Recent advancements in deep reinforcement learning have brought forth an impressive display of highly skilled artificial agents capable of complex intelligent behavior. In video games, these artificial agents are increasingly deployed as…
In this paper we explore the theoretical boundaries of planning in a setting where no model of the agent's actions is given. Instead of an action model, a set of successfully executed plans are given and the task is to generate a plan that…
We study a model of moral hazard with heterogeneous beliefs where each of agent's actions gives rise to a pair of probability distributions over output levels, one representing the beliefs of the agent and the other those of the principal.…
In this paper, we present a probabilistic adaptation of an Assume/Guarantee contract formalism. For the sake of generality, we assume that the extended state machines used in the contracts and implementations define sets of runs on a given…
We introduce a model of probabilistic verification in mechanism design. The principal elicits a message from the agent and then selects a test to give the agent. The agent's true type determines the probability with which he can pass each…
In this work we address the problem of finding feasible policies for Constrained Markov Decision Processes under probability one constraints. We argue that stationary policies are not sufficient for solving this problem, and that a rich…
In the bounded confidence model the opinions of a set of agents evolve over discrete time steps. In each round an agent averages the opinion of all agents whose opinions are at most a certain threshold apart. Here we assume that the…
Abstract argumentation offers an appealing way of representing and evaluating arguments and counterarguments. This approach can be enhanced by a probability assignment to each argument. There are various interpretations that can be ascribed…
Agents' judgment depends on perception and previous knowledge. Assuming that previous knowledge depends on perception, we can say that judgment depends on perception. So, if judgment depends on perception, can agents judge that they have…
Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…
We study the interpersonal trust of a population of agents, asking whether chance may decide if a population ends up in a high trust or low trust state. We model this by a discrete time, random matching stochastic coordination game. Agents…
Ramsey (1926) sketches a proposal for measuring the subjective probabilities of an agent by their observable preferences, assuming that the agent is an expected utility maximizer. I show how to extend the spirit of Ramsey's method to a…
How do we ascribe subjective probability? In decision theory, this question is often addressed by representation theorems, going back to Ramsey (1926), which tell us how to define or measure subjective probability by observable preferences.…
Assistive devices must determine both what a user intends to do and how reliable that prediction is before providing support. We introduce a safety-critical triggering framework based on calibrated probabilities for multimodal next-action…
When a human receives a prediction or recommended course of action from an intelligent agent, what additional information, beyond the prediction or recommendation itself, does the human require from the agent to decide whether to trust or…
When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for…