Agent Incentives: A Causal Perspective

Authors: Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg11487-11495

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present a framework for analysing agent incentives using causal influence diagrams. We establish that a well-known criterion for value of information is complete. We propose a new graphical criterion for value of control, establishing its soundness and completeness. We also introduce two new concepts for incentive analysis: response incentives indicate which changes in the environment affect an optimal decision, while instrumental control incentives establish whether an agent can influence its utility via a variable X. For both new concepts, we provide sound and complete graphical criteria.
Researcher Affiliation Collaboration Tom Everitt,*1* Ryan Carey,*2 Eric D. Langlois,*1,3,4 Pedro A. Ortega,1 Shane Legg1 1Deep Mind, 2University of Oxford, 3University of Toronto, 4Vector Institute tomeveritt@google.com, ry.duff@gmail.com, edl@cs.toronto.edu, pedroortega@google.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper states 'An open-source Python implementation of CIDs has recently been developed5 (Fox et al. 2021). 5https://github.com/causalincentives/pycid'. This refers to a general implementation of CIDs, not explicitly the specific code for the theoretical methodology described in this paper.
Open Datasets No The paper is theoretical and does not report on experiments using datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe experimental validation with dataset splits.
Hardware Specification No The paper is theoretical and does not describe any experimental setup involving specific hardware.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers for reproducibility of experiments.
Experiment Setup No The paper is theoretical and does not describe any experimental setup or hyperparameter details.