research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
share
research
∙
07/08/2023
Measuring the Success of Diffusion Models at Imitating Human Artists
Modern diffusion models have set the state-of-the-art in AI image genera...
research
∙
06/15/2023
Explore, Establish, Exploit: Red Teaming Language Models from Scratch
Deploying Large language models (LLMs) can pose hazards from harmful out...
research
∙
02/13/2023
Recommending to Strategic Users
Recommendation systems are pervasive in the digital economy. An importan...
research
∙
11/18/2022
Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks
Deep neural networks (DNNs) are powerful, but they can make mistakes tha...
research
∙
09/05/2022
White-Box Adversarial Policies in Deep Reinforcement Learning
Adversarial examples against AI systems pose both risks via malicious at...
research
∙
08/22/2022
Get It in Writing: Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL
Multi-agent reinforcement learning (MARL) is a powerful tool for trainin...
research
∙
08/01/2022
Towards Psychologically-Grounded Dynamic Preference Models
Designing recommendation systems that serve content aligned with time va...
research
∙
07/27/2022
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
The last decade of machine learning has seen drastic increases in scale ...
research
∙
07/20/2022
Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
Recommender systems are the algorithms which select, filter, and persona...
research
∙
06/16/2022
How to talk so your robot will learn: Instructions, descriptions, and pragmatics
From the earliest years of our lives, humans use language to express our...
research
∙
04/25/2022
Estimating and Penalizing Induced Preference Shifts in Recommender Systems
The content that a recommender system (RS) shows to users influences the...
research
∙
04/11/2022
Linguistic communication as (inverse) reward design
Natural language is an intuitive and expressive way to communicate rewar...
research
∙
12/06/2021
Guided Imitation of Task and Motion Planning
While modern policy optimization methods can do complex manipulation fro...
research
∙
07/22/2021
What are you optimizing for? Aligning Recommender Systems with Human Values
We describe cases where real recommender systems were modified in the se...
research
∙
07/01/2021
When Curation Becomes Creation: Algorithms, Microcontent, and the Vanishing Distinction between Platforms and Creators
Ever since social activity on the Internet began migrating from the wild...
research
∙
02/07/2021
Consequences of Misaligned AI
AI systems often rely on two key components: a specified goal or reward ...
research
∙
12/29/2020
Multi-Principal Assistance Games: Definition and Collegial Mechanisms
We introduce the concept of a multi-principal assistance game (MPAG), an...
research
∙
07/19/2020
Multi-Principal Assistance Games
Assistance games (also known as cooperative inverse reinforcement learni...
research
∙
01/25/2020
Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors
How can societies learn to enforce and comply with social norms? Here we...
research
∙
06/06/2019
An Extensible Interactive Interface for Agent Design
In artificial intelligence, we often specify tasks through a reward func...
research
∙
05/02/2019
Adversarial Training with Voronoi Constraints
Adversarial examples are a pervasive phenomenon of machine learning mode...
research
∙
02/26/2019
Conservative Agency via Attainable Utility Preservation
Reward functions are often misspecified. An agent optimizing an incorrec...
research
∙
01/24/2019
The Assistive Multi-Armed Bandit
Learning preferences implicit in the choices humans make is a well studi...
research
∙
01/04/2019
On the Utility of Model Learning in HRI
Fundamental to robotics is the debate between model-based and model-free...
research
∙
12/21/2018
Human-AI Learning Performance in Multi-Armed Bandits
People frequently face challenging decision-making problems in which out...
research
∙
11/03/2018
Legible Normativity for AI Alignment: The Value of Silly Rules
It has become commonplace to assert that autonomous agents will have to ...
research
∙
11/01/2018
On the Geometry of Adversarial Examples
Adversarial examples are a pervasive phenomenon of machine learning mode...
research
∙
09/09/2018
Active Inverse Reward Design
Reward design, the problem of selecting an appropriate reward function f...
research
∙
06/11/2018
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Our goal is for AI systems to correctly identify and act according to th...
research
∙
06/07/2018
Simplifying Reward Design through Divide-and-Conquer
Designing a good reward function is essential to robot planning and rein...
research
∙
04/12/2018
Incomplete Contracting and AI Alignment
We suggest that the analysis of incomplete contracting developed by law ...
research
∙
02/05/2018
Expressive Robot Motion Timing
Our goal is to enable robots to time their motion in a way that is purpo...
research
∙
11/08/2017
Inverse Reward Design
Autonomous agents optimize the reward function we give them. What they d...
research
∙
07/20/2017
Pragmatic-Pedagogic Value Alignment
For an autonomous system to provide value (e.g., to customers, designers...
research
∙
05/28/2017
Should Robots be Obedient?
Intuitively, obedience -- following the order that a human gives -- seem...
research
∙
11/24/2016
The Off-Switch Game
It is clear that one of the primary tools we can use to mitigate the pot...
research
∙
06/09/2016