Owain Evans

Alexander Tamas Postdoc in Artificial Intelligence, University of Oxford

I work on AI Safety and Reinforcement Learning at the Future of Humanity Institute (directed by Nick Bostrom). I also lead a project on "Inferring Human Preferences" with Andreas Stuhlmüller of Stanford University. My PhD is from MIT, where I worked on cognitive science, probabilistic programming, and philosophy of science.

If you'd like to do an internship with me, send your CV and statement of interest here.

My name is pronounced "O-wine".

Email | Google Scholar | LinkedIn | Facebook

Research

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Saunders S., Sastry G., Stuhlmüller A., Evans O. (2017)
Arxiv Pre-print
(Blogpost, Atari Videos, Slides)

When Will AI Exceed Human Performance? Evidence from AI Experts.
Grace K., Salvatier J., Zhang B., Dafoe A., Evans O. (2017)
Arxiv Pre-print
(Covered by BBC News, New Scientist, Newsweek, and more)

Model Mis-specification and Inverse Reinforcement Learning.
(Essay co-authored with Jacob Steinhardt, 2017).

Agentmodels.org: Modeling Agents with Probabilistic Programs.
Evans O., Stuhlmüller A., Salvatier J., Filan D. (2017)
Interactive Online Book

Agent-Agnostic Human-in-the-Loop Reinforcement Learning.
Abel D., Salvatier J., Stuhlmüller A., Evans O. (2016)
NIPS Workshop

Active Reinforcement Learning: Observing Rewards at a Cost.
Krueger D., Leike J, Salvatier J., Evans O. (2016)
NIPS Workshop

Learning the Preferences of Ignorant, Inconsistent Agents.
Evans O., Stuhlmüller A., Goodman N. (2016)
AAAI

Learning the Preferences of Bounded Agents.
Evans O., Stuhlmüller A., Goodman N. (2015)
NIPS Workshop

Learning Structured Preferences.
Evans O., Bergen L., Tenenbaum J. (2012)
Cogsci

Help or hinder: Bayesian models of social goal inference.
Ullman T., Baker C., Macindoe O., Evans O., Goodman N., & Tenenbaum J. (2010)
NIPS

Bayesian Computational Models for Inferring Preferences (2015)
MIT Dissertation

Talks

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
(Slides for talks at Cambridge Centre for the Future of Intelligence and Google Deepmind)

Automated Corporations and AI Risk
(Informal talk at Oxford University)

Agent-agnostic Human-in-the-loop Reinforcement Learning
(Slides for talks at U. Toronto and Deepmind)

Learning the Preferences of Ignorant, Inconsistent Agents
(Slides for oral presentation at AAAI 2016)

Learning Human Preferences
(Short talk at MIT)

Recent Collaborators

description here
Andreas Stuhlmüller 		description here
John Salvatier 		description here
Katja Grace
description here
Jan Leike 		description here
David Abel 		description here
David Krueger
description here
Allan Dafoe 		description here
Vlad Firoiu 		description here
William Saunders
description here
Baobao Zhang 		description here
Girish Sastry

Adapted from Matei Zaharia and Andreas Viklund.