The Incentives that Shape Behaviour

01/20/2020
by   Ryan Carey, et al.
9

Which variables does an agent have an incentive to control with its decision, and which variables does it have an incentive to respond to? We formalise these incentives, and demonstrate unique graphical criteria for detecting them in any single decision causal influence diagram. To this end, we introduce structural causal influence models, a hybrid of the influence diagram and structural causal model frameworks. Finally, we illustrate how these incentives predict agent incentives in both fairness and AI safety applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2021

Agent Incentives: A Causal Perspective

We present a framework for analysing agent incentives using causal influ...
research
04/21/2022

Path-Specific Objectives for Safer Agent Incentives

We present a general framework for training safe agents whose naive ince...
research
02/27/2013

A Decision-Based View of Causality

Most traditional models of uncertainty have focused on the associational...
research
03/13/2013

Structural Controllability and Observability in Influence Diagrams

Influence diagram is a graphical representation of belief networks with ...
research
07/10/2020

AGI Agent Safety by Iteratively Improving the Utility Function

While it is still unclear if agents with Artificial General Intelligence...
research
02/13/2013

Constraining Influence Diagram Structure by Generative Planning: An Application to the Optimization of Oil Spill Response

This paper works through the optimization of a real world planning probl...
research
07/22/2021

Graphical Influence Diagnostics for Changepoint Models

Changepoint models enjoy a wide appeal in a variety of disciplines to mo...

Please sign up or login with your details

Forgot password? Click here to reset