Tom Everitt

According to our database, Tom Everitt authored at least 43 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Measuring Goal-Directedness.

Matt MacDermott, James Fox, Francesco Belardinelli, Tom Everitt

CoRR, 2024

A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI.

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

CoRR, 2024

Robust agents learn causal world models.

Jonathan Richens, Tom Everitt

Proceedings of the Twelfth International Conference on Learning Representations, 2024

The Reasons that Agents Act: Intention and Instrumental Goals.

Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

Discovering Agents (Abstract Reprint).

Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Reasoning about Causality in Games (Abstract Reprint).

Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Discovering agents.

Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt

Artif. Intell., September, 2023

Reasoning about causality in games.

Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge

Artif. Intell., July, 2023

Characterising Decision Theories with Mechanised Causal Graphs.

Matt MacDermott, Tom Everitt, Francesco Belardinelli

CoRR, 2023

Human Control: Definitions and Algorithms.

Ryan Carey, Tom Everitt

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Honesty Is the Best Policy: Defining and Mitigating AI Deception.

Francis Ward, Francesca Toni, Francesco Belardinelli, Tom Everitt

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

A Complete Criterion for Value of Information in Soluble Influence Diagrams.

Chris van Merwijk, Ryan Carey, Tom Everitt

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

Path-Specific Objectives for Safer Agent Incentives.

Sebastian Farquhar, Ryan Carey, Tom Everitt

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness.

Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.

Tom Everitt, Marcus Hutter, Ramana Kumar, Victoria Krakovna

Synth., 2021

Shaking the foundations: delusions in sequence models for interaction and control.

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

CoRR, 2021

Alignment of Language Agents.

Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, Geoffrey Irving

CoRR, 2021

PyCID: A Python Library for Causal Influence Diagrams.

James Fox, Tom Everitt, Ryan Carey, Eric D. Langlois, Alessandro Abate, Michael J. Wooldridge

Proceedings of the 20th Python in Science Conference 2021 (SciPy 2021), Virtual Conference, July 12, 2021

Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice.

Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael J. Wooldridge

Proceedings of the AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, 2021

How RL Agents Behave When Their Actions Are Modified.

Eric D. Langlois, Tom Everitt

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Agent Incentives: A Causal Perspective.

Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Avoiding Tampering Incentives in Deep RL via Decoupled Approval.

Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg

CoRR, 2020

REALab: An Embedded Perspective on Tampering.

Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, Shane Legg

CoRR, 2020

The Incentives that Shape Behaviour.

Ryan Carey, Eric D. Langlois, Tom Everitt, Shane Legg

CoRR, 2020

2019

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective.

Tom Everitt, Marcus Hutter

CoRR, 2019

Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings.

Tom Everitt, Pedro A. Ortega, Elizabeth Barnes, Shane Legg

CoRR, 2019

Modeling AGI Safety Frameworks with Causal Influence Diagrams.

Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg

Proceedings of the Workshop on Artificial Intelligence Safety 2019 co-located with the 28th International Joint Conference on Artificial Intelligence, 2019

2018

Scalable agent alignment via reward modeling: a research direction.

Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg

CoRR, 2018

AGI Safety Literature Review.

Tom Everitt, Gary Lea, Marcus Hutter

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

2017

AI Safety Gridworlds.

Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg

CoRR, 2017

Reinforcement Learning with a Corrupted Reward Channel.

Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg

CoRR, 2017

Count-Based Exploration in Feature Space for Reinforcement Learning.

Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Reinforcement Learning with a Corrupted Reward Channel.

Tom Everitt, Victoria Krakovna, Laurent Orseau, Shane Legg

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

A Game-Theoretic Analysis of the Off-Switch Game.

Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, Marcus Hutter

Proceedings of the Artificial General Intelligence - 10th International Conference, 2017

2016

Death and Suicide in Universal Artificial Intelligence.

Jarryd Martin, Tom Everitt, Marcus Hutter

Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

Avoiding Wireheading with Value Reinforcement Learning.

Tom Everitt, Marcus Hutter

Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

Self-Modification of Policy and Utility Function in Rational Agents.

Tom Everitt, Daniel Filan, Mayank Daswani, Marcus Hutter

Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

2015

A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem.

Tom Everitt, Marcus Hutter

CoRR, 2015

Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search.

Tom Everitt, Marcus Hutter

Proceedings of the AI 2015: Advances in Artificial Intelligence, 2015

Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search.

Tom Everitt, Marcus Hutter

Proceedings of the AI 2015: Advances in Artificial Intelligence, 2015

Sequential Extensions of Causal and Evidential Decision Theory.

Tom Everitt, Jan Leike, Marcus Hutter

Proceedings of the Algorithmic Decision Theory - 4th International Conference, 2015

2014

Can we measure the difficulty of an optimization problem?

Tansu Alpcan, Tom Everitt, Marcus Hutter

Proceedings of the 2014 IEEE Information Theory Workshop, 2014

Free Lunch for optimisation under the universal distribution.

Tom Everitt, Tor Lattimore, Marcus Hutter

Proceedings of the IEEE Congress on Evolutionary Computation, 2014