English
Related papers

Related papers: Agent Incentives: A Causal Perspective

200 papers

Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction using causal influence diagrams, we can…

Artificial Intelligence · Computer Science 2022-01-21 Tom Everitt , Pedro A. Ortega , Elizabeth Barnes , Shane Legg

We introduce three concepts that describe an agent's incentives: response incentives indicate which variables in the environment, such as sensitive demographic information, affect the decision under the optimal policy. Instrumental control…

Artificial Intelligence · Computer Science 2025-06-24 Ryan Carey , Eric Langlois , Chris van Merwijk , Shane Legg , Tom Everitt

Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if…

Artificial Intelligence · Computer Science 2025-11-18 Rhys Howard , Nick Hawes , Lars Kunze

Causal reasoning has been an indispensable capability for humans and other intelligent animals to interact with the physical world. In this work, we propose to endow an artificial agent with the capability of causal reasoning for completing…

Machine Learning · Computer Science 2019-10-07 Suraj Nair , Yuke Zhu , Silvio Savarese , Li Fei-Fei

We study the design of optimal incentives in sequential processes. To do so, we consider a basic and fundamental model in which an agent initiates a value-creating sequential process through costly investment with random success. If…

Theoretical Economics · Economics 2023-11-22 Jens Gudmundsson , Jens Leth Hougaard , Juan D. Moreno-Ternero , Lars Peter Østerdal

Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification -- and modelling…

Artificial Intelligence · Computer Science 2022-08-25 Zachary Kenton , Ramana Kumar , Sebastian Farquhar , Jonathan Richens , Matt MacDermott , Tom Everitt

Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards…

Machine Learning · Computer Science 2024-02-13 Rati Devidze , Parameswaran Kamalaruban , Adish Singla

Influence diagrams have recently been used to analyse the safety and fairness properties of AI systems. A key building block for this analysis is a graphical criterion for value of information (VoI). This paper establishes the first…

Artificial Intelligence · Computer Science 2022-02-24 Chris van Merwijk , Ryan Carey , Tom Everitt

As machine learning systems become more powerful they also become increasingly unpredictable and opaque. Yet, finding human-understandable explanations of how they work is essential for their safe deployment. This technical report…

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an…

Artificial Intelligence · Computer Science 2023-01-05 Stas Tiomkin , Ilya Nemenman , Daniel Polani , Naftali Tishby

As society transitions towards an AI-based decision-making infrastructure, an ever-increasing number of decisions once under control of humans are now delegated to automated systems. Even though such developments make various parts of…

Artificial Intelligence · Computer Science 2023-06-09 Drago Plecko , Elias Bareinboim

In science, macro level descriptions of the causal interactions within complex, dynamical systems are typically deemed convenient, but ultimately reducible to a complete causal account of the underlying micro constituents. Yet, such a…

Neurons and Cognition · Quantitative Biology 2020-04-02 Larissa Albantakis , Francesco Massari , Maggie Beheler-Amass , Giulio Tononi

AI has revolutionised decision-making across various fields. Yet human judgement remains paramount for high-stakes decision-making. This has fueled explorations of collaborative decision-making between humans and AI systems, aiming to…

Human-Computer Interaction · Computer Science 2026-01-22 Simran Kaur , Sara Salimzadeh , Ujwal Gadiraju

Traffic scenarios are inherently interactive. Multiple decision-makers predict the actions of others and choose strategies that maximize their rewards. We view these interactions from the perspective of game theory which introduces various…

Machine Learning · Computer Science 2020-04-28 Christian Muench , Frans A. Oliehoek , Dariu M. Gavrila

Causal games are probabilistic graphical models that enable causal queries to be answered in multi-agent settings. They extend causal Bayesian networks by specifying decision and utility variables to represent the agents' degrees of freedom…

Computer Science and Game Theory · Computer Science 2024-06-14 Manuj Mishra , James Fox , Michael Wooldridge

A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distinct from those of any individual. More generally, determining…

Artificial Intelligence · Computer Science 2026-05-04 Frederik Hytting Jørgensen , Sebastian Weichwald , Lewis Hammond

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most…

AI agents are commonly trained with large datasets of demonstrations of human behavior. However, not all behaviors are equally safe or desirable. Desired characteristics for an AI agent can be expressed by assigning desirability scores,…

Machine Learning · Computer Science 2024-05-08 Tim Franzmeyer , Edith Elkind , Philip Torr , Jakob Foerster , Joao Henriques

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make…

We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisal of a set of observations measuring the extent to which…

Neurons and Cognition · Quantitative Biology 2020-10-14 Alvaro Ovalle , Simon M. Lucas
‹ Prev 1 2 3 10 Next ›