Dylan Hadfield-Menell, UC Berkeley
researchactive

The Principal-Agent Alignment Problem in AI

Dylan Hadfield-Menell, UC Berkeley

View original resource

Hadfield-Menell's Berkeley technical report formalises AI alignment as a principal-agent problem with incomplete contracts, drawing on mechanism design. Introduces inverse reward design and cooperative inverse reinforcement learning as alignment approaches.

Tags

agentic AIgovernance-frameworks

At a glance

Published

2021

Jurisdiction

United States

Category

Governance frameworks

Access

Public access

More in Governance frameworks

Practices for Governing Agentic AI Systems

Yonadav Shavit et al., OpenAI • 2023

Infrastructure for AI Agents

Alan Chan et al., Centre for the Governance of AI • 2025

AI Agents: Governing Autonomy in the Digital Age

Joe Kwon, Center for AI Policy • 2025

Related resources

Practices for governing agentic AI systems: OpenAI's seven safety principles

Governance frameworks • OpenAI

Taxonomy of Failure Mode in Agentic AI Systems

Risk taxonomies • Microsoft

The agentic AI landscape and its conceptual foundations

Foundations • OECD

Build your AI governance program

VerifyWise helps you implement AI governance frameworks, track compliance, and manage risk across your AI systems.

Explore the libraryStart free trial
The Principal-Agent Alignment Problem in AI | VerifyWise AI Governance Library