MIT AI Risk Repository · Risk Category · 39.17.00

Rationality

Open the MIT Risk Navigator All entries from Saghiri2022

Description

The concept of rational agency has long been considered as a critical role in defining intelligent agents. Rationality computation plays a key role in distributed machine learning, multi-agent systems, game theory, and also AGI... Unfortunately, a lack of required information prevents the creation of an agent with perfect rationality

From A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: —
Subdomain: —
Causal entity: Not coded
Intent: Not coded
Timing: Not coded

Other entries from Saghiri2022

Problem Identification and Formulation Risk Category
Energy Consumption Risk Category · 6.6
Data Issues Risk Category · 1.1
Robustness and Reliability Risk Category · 7.3
Cheating and Deception Risk Category · 7.2
Security Risk Category · 2.2
Privacy Risk Category · 2.1
Fairness Risk Category · 1.3
Explainable AI Risk Category
Responsibility Risk Category · 6.5
Controllability Risk Category · 7.1
Predictability Risk Category · 7.3