Tom Everitt

73 papers A* 15A 3B 2Journal 43Unranked 9
YearRankTypeTitle / Venue / Authors
2025 J jnl
An Approach to Technical AGI Safety and Security.
CoRR
Rohin Shah, Alex Irpan, Alexander Matt Turner, Anna Wang, Arthur Conmy, David Lindner, Jonah Brown-Cohen, Lewis Ho, Neel Nanda, Raluca Ada Popa, Rishub Jain, Rory Greig, Samuel Albanie, Scott Emmons, Sebastian Farquhar, Sébastien Krier, Senthooran Rajamanoharan, Sophie Bridgers, Tobi Ijitoye, Tom Everitt, Victoria Krakovna, Vikrant Varma, Vladimir Mikulik, Zachary Kenton, Dave Orr, Shane Legg, Noah D. Goodman, Allan Dafoe, Four Flynn, Anca D. Dragan
2025 J jnl
Evaluating the Goal-Directedness of Large Language Models.
CoRR
Tom Everitt, Cristina Garbacea, Alexis Bellot, Jonathan Richens, Henry Papadatos, Siméon Campos, Rohin Shah
2025 A* conf
General agents need world models.
ICML
Jonathan Richens, Tom Everitt, David Abel
2025 J jnl
General agents need world models.
CoRR
Jonathan Richens, David Abel, Alexis Bellot, Tom Everitt
2025 J jnl
Incentives for responsiveness, instrumental control and impact.
Artif. Intell.
Ryan Carey, Eric D. Langlois, Chris van Merwijk, Shane Legg, Tom Everitt
2025 A* conf
The Limits of Predicting Agents from Behaviour.
ICML
Alexis Bellot, Jonathan Richens, Tom Everitt
2025 J jnl
The Limits of Predicting Agents from Behaviour.
CoRR
Alexis Bellot, Jonathan Richens, Tom Everitt
2024 J jnl
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI.
CoRR
Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery, Geoff Keeling, Zachary Kenton, Zaria Jalan, Nahema Marchal, Arianna Manzini, Toby Shevlane, Shannon Vallor, Daniel Susser, Matija Franklin, Sophie Bridgers, Harry Law, Matthew Rahtz, Murray Shanahan, Michael Henry Tessler, Arthur Douillard, Tom Everitt, Sasha Brown
2024 A* conf
Discovering Agents (Abstract Reprint).
AAAI
Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
2024 A* conf
Measuring Goal-Directedness.
NeurIPS
Matt MacDermott, James Fox, Francesco Belardinelli, Tom Everitt
2024 J jnl
Measuring Goal-Directedness.
CoRR
Matt MacDermott, James Fox, Francesco Belardinelli, Tom Everitt
2024 A* conf
Reasoning about Causality in Games (Abstract Reprint).
AAAI
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
2024 A* conf
Robust agents learn causal world models.
ICLR
Jonathan Richens, Tom Everitt
2024 J jnl
Robust agents learn causal world models.
CoRR
Jonathan Richens, Tom Everitt
2024 A conf
The Reasons that Agents Act: Intention and Instrumental Goals.
AAMAS
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt
2024 J jnl
The Reasons that Agents Act: Intention and Instrumental Goals.
CoRR
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt
2023 J jnl
Characterising Decision Theories with Mechanised Causal Graphs.
CoRR
Matt MacDermott, Tom Everitt, Francesco Belardinelli
2023 J jnl
Discovering agents.
Artif. Intell.
Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
2023 A* conf
Honesty Is the Best Policy: Defining and Mitigating AI Deception.
NeurIPS
Francis Ward, Francesca Toni, Francesco Belardinelli, Tom Everitt
2023 J jnl
Honesty Is the Best Policy: Defining and Mitigating AI Deception.
CoRR
Francis Rhys Ward, Francesco Belardinelli, Francesca Toni, Tom Everitt
2023 A conf
Human Control: Definitions and Algorithms.
UAI
Ryan Carey, Tom Everitt
2023 J jnl
Human Control: Definitions and Algorithms.
CoRR
Ryan Carey, Tom Everitt
2023 J jnl
Reasoning about Causality in Games.
CoRR
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
2023 J jnl
Reasoning about causality in games.
Artif. Intell.
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
2022 A* conf
A Complete Criterion for Value of Information in Soluble Influence Diagrams.
AAAI
Chris van Merwijk, Ryan Carey, Tom Everitt
2022 J jnl
A Complete Criterion for Value of Information in Soluble Influence Diagrams.
CoRR
Chris van Merwijk, Ryan Carey, Tom Everitt
2022 J jnl
Discovering Agents.
CoRR
Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
2022 A* conf
Path-Specific Objectives for Safer Agent Incentives.
AAAI
Sebastian Farquhar, Ryan Carey, Tom Everitt
2022 J jnl
Path-Specific Objectives for Safer Agent Incentives.
CoRR
Sebastian Farquhar, Ryan Carey, Tom Everitt
2022 A* conf
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness.
AAAI
Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt
2022 J jnl
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness.
CoRR
Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt
2021 A* conf
Agent Incentives: A Causal Perspective.
AAAI
Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg
2021 J jnl
Agent Incentives: A Causal Perspective.
CoRR
Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg
2021 J jnl
Alignment of Language Agents.
CoRR
Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, Geoffrey Irving
2021 A conf
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice.
AAMAS
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael J. Wooldridge
2021 J jnl
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice.
CoRR
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael J. Wooldridge
2021 A* conf
How RL Agents Behave When Their Actions Are Modified.
AAAI
Eric D. Langlois, Tom Everitt
2021 J jnl
How RL Agents Behave When Their Actions Are Modified.
CoRR
Eric D. Langlois, Tom Everitt
2021 — conf
PyCID: A Python Library for Causal Influence Diagrams.
SciPy
James Fox, Tom Everitt, Ryan Carey, Eric D. Langlois, Alessandro Abate, Michael J. Wooldridge
2021 J jnl
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
Synth.
Tom Everitt, Marcus Hutter, Ramana Kumar, Victoria Krakovna
2021 J jnl
Shaking the foundations: delusions in sequence models for interaction and control.
CoRR
Pedro A. Ortega, Markus Kunesch, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Joel Veness, Jonas Buchli, Jonas Degrave, Bilal Piot, Julien Pérolat, Tom Everitt, Corentin Tallec, Emilio Parisotto, Tom Erez, Yutian Chen, Scott E. Reed, Marcus Hutter, Nando de Freitas, Shane Legg
2020 J jnl
Avoiding Tampering Incentives in Deep RL via Decoupled Approval.
CoRR
Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg
2020 J jnl
REALab: An Embedded Perspective on Tampering.
CoRR
Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, Shane Legg
2020 J jnl
The Incentives that Shape Behaviour.
CoRR
Ryan Carey, Eric D. Langlois, Tom Everitt, Shane Legg
2019 — conf
Modeling AGI Safety Frameworks with Causal Influence Diagrams.
AISafety@IJCAI
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
2019 J jnl
Modeling AGI Safety Frameworks with Causal Influence Diagrams.
CoRR
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
2019 J jnl
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective.
CoRR
Tom Everitt, Marcus Hutter
2019 J jnl
Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings.
CoRR
Tom Everitt, Pedro A. Ortega, Elizabeth Barnes, Shane Legg
2018 A* conf
AGI Safety Literature Review.
IJCAI
Tom Everitt, Gary Lea, Marcus Hutter
2018 J jnl
AGI Safety Literature Review.
CoRR
Tom Everitt, Gary Lea, Marcus Hutter
2018 J jnl
Scalable agent alignment via reward modeling: a research direction.
CoRR
Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg
2017 — conf
A Game-Theoretic Analysis of the Off-Switch Game.
AGI
Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, Marcus Hutter
2017 J jnl
A Game-Theoretic Analysis of the Off-Switch Game.
CoRR
Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, Marcus Hutter
2017 J jnl
AI Safety Gridworlds.
CoRR
Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg
2017 — ed.
Artificial General Intelligence - 10th International Conference, AGI 2017, Melbourne, VIC, Australia, August 15-18, 2017, Proceedings
AGI
Tom Everitt, Ben Goertzel, Alexey Potapov
2017 A* conf
Count-Based Exploration in Feature Space for Reinforcement Learning.
IJCAI
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter
2017 J jnl
Count-Based Exploration in Feature Space for Reinforcement Learning.
CoRR
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter
2017 A* conf
Reinforcement Learning with a Corrupted Reward Channel.
IJCAI
Tom Everitt, Victoria Krakovna, Laurent Orseau, Shane Legg
2017 J jnl
Reinforcement Learning with a Corrupted Reward Channel.
CoRR
Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg
2016 — conf
Avoiding Wireheading with Value Reinforcement Learning.
AGI
Tom Everitt, Marcus Hutter
2016 J jnl
Avoiding Wireheading with Value Reinforcement Learning.
CoRR
Tom Everitt, Marcus Hutter
2016 — conf
Death and Suicide in Universal Artificial Intelligence.
AGI
Jarryd Martin, Tom Everitt, Marcus Hutter
2016 J jnl
Death and Suicide in Universal Artificial Intelligence.
CoRR
Jarryd Martin, Tom Everitt, Marcus Hutter
2016 J jnl
Free Lunch for Optimisation under the Universal Distribution.
CoRR
Tom Everitt, Tor Lattimore, Marcus Hutter
2016 — conf
Self-Modification of Policy and Utility Function in Rational Agents.
AGI
Tom Everitt, Daniel Filan, Mayank Daswani, Marcus Hutter
2016 J jnl
Self-Modification of Policy and Utility Function in Rational Agents.
CoRR
Tom Everitt, Daniel Filan, Mayank Daswani, Marcus Hutter
2015 J jnl
A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem.
CoRR
Tom Everitt, Marcus Hutter
2015 — conf
Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search.
Australasian Conference on Artificial Intelligence
Tom Everitt, Marcus Hutter
2015 — conf
Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search.
Australasian Conference on Artificial Intelligence
Tom Everitt, Marcus Hutter
2015 — conf
Sequential Extensions of Causal and Evidential Decision Theory.
ADT
Tom Everitt, Jan Leike, Marcus Hutter
2015 J jnl
Sequential Extensions of Causal and Evidential Decision Theory.
CoRR
Tom Everitt, Jan Leike, Marcus Hutter
2014 B conf
Can we measure the difficulty of an optimization problem?
ITW
Tansu Alpcan, Tom Everitt, Marcus Hutter
2014 B conf
Free Lunch for optimisation under the universal distribution.
IEEE Congress on Evolutionary Computation
Tom Everitt, Tor Lattimore, Marcus Hutter