Alert button
Picture for Owain Evans

Owain Evans

Alert button

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Sep 08, 2021
Stephanie Lin, Jacob Hilton, Owain Evans

Figure 1 for TruthfulQA: Measuring How Models Mimic Human Falsehoods
Figure 2 for TruthfulQA: Measuring How Models Mimic Human Falsehoods
Figure 3 for TruthfulQA: Measuring How Models Mimic Human Falsehoods
Figure 4 for TruthfulQA: Measuring How Models Mimic Human Falsehoods
Viaarxiv icon

Active Reinforcement Learning: Observing Rewards at a Cost

Nov 24, 2020
David Krueger, Jan Leike, Owain Evans, John Salvatier

Figure 1 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 2 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 3 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 4 for Active Reinforcement Learning: Observing Rewards at a Cost
Viaarxiv icon

Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art

Nov 16, 2019
Owain Evans

Figure 1 for Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
Figure 2 for Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
Figure 3 for Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
Figure 4 for Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art
Viaarxiv icon

Generalizing from a few environments in safety-critical reinforcement learning

Jul 02, 2019
Zachary Kenton, Angelos Filos, Owain Evans, Yarin Gal

Figure 1 for Generalizing from a few environments in safety-critical reinforcement learning
Figure 2 for Generalizing from a few environments in safety-critical reinforcement learning
Figure 3 for Generalizing from a few environments in safety-critical reinforcement learning
Figure 4 for Generalizing from a few environments in safety-critical reinforcement learning
Viaarxiv icon

When Will AI Exceed Human Performance? Evidence from AI Experts

May 03, 2018
Katja Grace, John Salvatier, Allan Dafoe, Baobao Zhang, Owain Evans

Figure 1 for When Will AI Exceed Human Performance? Evidence from AI Experts
Figure 2 for When Will AI Exceed Human Performance? Evidence from AI Experts
Figure 3 for When Will AI Exceed Human Performance? Evidence from AI Experts
Figure 4 for When Will AI Exceed Human Performance? Evidence from AI Experts
Viaarxiv icon

Active Reinforcement Learning with Monte-Carlo Tree Search

Mar 26, 2018
Sebastian Schulze, Owain Evans

Figure 1 for Active Reinforcement Learning with Monte-Carlo Tree Search
Figure 2 for Active Reinforcement Learning with Monte-Carlo Tree Search
Figure 3 for Active Reinforcement Learning with Monte-Carlo Tree Search
Figure 4 for Active Reinforcement Learning with Monte-Carlo Tree Search
Viaarxiv icon

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Feb 20, 2018
Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei

Figure 1 for The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Viaarxiv icon

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention

Jul 17, 2017
William Saunders, Girish Sastry, Andreas Stuhlmueller, Owain Evans

Figure 1 for Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Figure 2 for Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Figure 3 for Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Viaarxiv icon

Agent-Agnostic Human-in-the-Loop Reinforcement Learning

Jan 15, 2017
David Abel, John Salvatier, Andreas Stuhlmüller, Owain Evans

Figure 1 for Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Figure 2 for Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Figure 3 for Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Figure 4 for Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Viaarxiv icon