Agent Incentives: A Causal Perspective


  • Tom Everitt DeepMind
  • Ryan Carey University of Oxford
  • Eric D. Langlois DeepMind; University of Toronto; Vector Institute
  • Pedro A. Ortega DeepMind
  • Shane Legg DeepMind



Safety, Robustness & Trustworthiness


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. We show by example how these results can help with evaluating the safety and fairness of an AI system




How to Cite

Everitt, T., Carey, R., Langlois, E. D., Ortega, P. A., & Legg, S. (2021). Agent Incentives: A Causal Perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11487-11495.



AAAI Technical Track on Philosophy and Ethics of AI