MIT AI Risk Repository · Risk Sub-Category · 34.01.02

Goal Misgeneralization

Category: Causes of Misalignment

Description

"Goal Misgeneralization: Goal misgeneralization is another failure mode, wherein the agent actively pursuesobjectives distinct from the training objectives in deployment while retaining the capabilities it acquired duringtraining (Di Langosco et al., 2022). For instance, in CoinRun games, the agent frequently prefers reachingthe end of a level, often neglecting relocated coins during testing scenarios. Di Langosco et al. (2022) drawattention to the fundamental disparity between capability generalization and goal generalization, emphasizing howthe inductive biases inherent in the model and its

From AI Alignment: A Comprehensive Survey (Ji2023), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

Subdomain definition: AI systems acting in conflict with human goals or values, especially the goals of designers or users, or ethical standards. These misaligned behaviors may be introduced by humans during design and development, such as through reward hacking and goal misgeneralisation, or may result from AI using dangerous capabilities such as manipulation, deception, situational awareness to seek power, self-proliferate, or achieve other goals.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from Ji2023