Tom Everitt

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 56

Top Topics

Influence Diagrams

Reinforcement Learning

Top Venues

Publications

Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
Discovering Agents (Abstract Reprint). AAAI (2024)
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt
The Reasons that Agents Act: Intention and Instrumental Goals. AAMAS (2024)
Jonathan Richens, Tom Everitt
Robust agents learn causal world models. CoRR (2024)
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
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI. CoRR (2024)
Jonathan Richens, Tom Everitt
Robust agents learn causal world models. ICLR (2024)
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt
The Reasons that Agents Act: Intention and Instrumental Goals. CoRR (2024)
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
Reasoning about Causality in Games (Abstract Reprint). AAAI (2024)
Francis Rhys Ward, Francesco Belardinelli, Francesca Toni, Tom Everitt
Honesty Is the Best Policy: Defining and Mitigating AI Deception. CoRR (2023)
Francis Ward, Francesca Toni, Francesco Belardinelli, Tom Everitt
Honesty Is the Best Policy: Defining and Mitigating AI Deception. NeurIPS (2023)
Ryan Carey, Tom Everitt
Human Control: Definitions and Algorithms. UAI (2023)
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
Reasoning about Causality in Games. CoRR (2023)
Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
Discovering agents. Artif. Intell. 322 (2023)
Matt MacDermott, Tom Everitt, Francesco Belardinelli
Characterising Decision Theories with Mechanised Causal Graphs. CoRR (2023)
Lewis Hammond, James Fox, Tom Everitt, Ryan Carey, Alessandro Abate, Michael J. Wooldridge
Reasoning about causality in games. Artif. Intell. 320 (2023)
Ryan Carey, Tom Everitt
Human Control: Definitions and Algorithms. CoRR (2023)
Chris van Merwijk, Ryan Carey, Tom Everitt
A Complete Criterion for Value of Information in Soluble Influence Diagrams. CoRR (2022)
Chris van Merwijk, Ryan Carey, Tom Everitt
A Complete Criterion for Value of Information in Soluble Influence Diagrams. AAAI (2022)
Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness. CoRR (2022)
Sebastian Farquhar, Ryan Carey, Tom Everitt
Path-Specific Objectives for Safer Agent Incentives. AAAI (2022)
Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness. AAAI (2022)
Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
Discovering Agents. CoRR (2022)
Sebastian Farquhar, Ryan Carey, Tom Everitt
Path-Specific Objectives for Safer Agent Incentives. CoRR (2022)
Eric D. Langlois, Tom Everitt
How RL Agents Behave When Their Actions Are Modified. CoRR (2021)
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
Shaking the foundations: delusions in sequence models for interaction and control. CoRR (2021)
James Fox, Tom Everitt, Ryan Carey, Eric D. Langlois, Alessandro Abate, Michael J. Wooldridge
PyCID: A Python Library for Causal Influence Diagrams. SciPy (2021)
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael J. Wooldridge
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice. CoRR (2021)
Tom Everitt, Marcus Hutter, Ramana Kumar, Victoria Krakovna
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective. Synth. 198 (27) (2021)
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael J. Wooldridge
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice. AAMAS (2021)
Eric D. Langlois, Tom Everitt
How RL Agents Behave When Their Actions Are Modified. AAAI (2021)
Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg
Agent Incentives: A Causal Perspective. CoRR (2021)
Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, Geoffrey Irving
Alignment of Language Agents. CoRR (2021)
Tom Everitt, Ryan Carey, Eric D. Langlois, Pedro A. Ortega, Shane Legg
Agent Incentives: A Causal Perspective. AAAI (2021)
Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, Shane Legg
REALab: An Embedded Perspective on Tampering. CoRR (2020)
Ryan Carey, Eric D. Langlois, Tom Everitt, Shane Legg
The Incentives that Shape Behaviour. CoRR (2020)
Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg
Avoiding Tampering Incentives in Deep RL via Decoupled Approval. CoRR (2020)
Tom Everitt, Marcus Hutter
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective. CoRR (2019)
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
Modeling AGI Safety Frameworks with Causal Influence Diagrams. CoRR (2019)
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
Modeling AGI Safety Frameworks with Causal Influence Diagrams. AISafety@IJCAI (2019)
Tom Everitt, Pedro A. Ortega, Elizabeth Barnes, Shane Legg
Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings. CoRR (2019)
Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg
Scalable agent alignment via reward modeling: a research direction. CoRR (2018)
Tom Everitt, Gary Lea, Marcus Hutter
AGI Safety Literature Review. CoRR (2018)
Tom Everitt, Gary Lea, Marcus Hutter
AGI Safety Literature Review. IJCAI (2018)
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter
Count-Based Exploration in Feature Space for Reinforcement Learning. CoRR (2017)
Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, Marcus Hutter
A Game-Theoretic Analysis of the Off-Switch Game. CoRR (2017)
Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, Marcus Hutter
A Game-Theoretic Analysis of the Off-Switch Game. AGI (2017)
Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg
AI Safety Gridworlds. CoRR (2017)
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter
Count-Based Exploration in Feature Space for Reinforcement Learning. IJCAI (2017)
Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg
Reinforcement Learning with a Corrupted Reward Channel. CoRR (2017)
Tom Everitt, Victoria Krakovna, Laurent Orseau, Shane Legg
Reinforcement Learning with a Corrupted Reward Channel. IJCAI (2017)
Jarryd Martin, Tom Everitt, Marcus Hutter
Death and Suicide in Universal Artificial Intelligence. AGI (2016)
Tom Everitt, Daniel Filan, Mayank Daswani, Marcus Hutter
Self-Modification of Policy and Utility Function in Rational Agents. AGI (2016)
Tom Everitt, Tor Lattimore, Marcus Hutter
Free Lunch for Optimisation under the Universal Distribution. CoRR (2016)
Tom Everitt, Daniel Filan, Mayank Daswani, Marcus Hutter
Self-Modification of Policy and Utility Function in Rational Agents. CoRR (2016)
Tom Everitt, Marcus Hutter
Avoiding Wireheading with Value Reinforcement Learning. AGI (2016)
Jarryd Martin, Tom Everitt, Marcus Hutter
Death and Suicide in Universal Artificial Intelligence. CoRR (2016)
Tom Everitt, Marcus Hutter
Avoiding Wireheading with Value Reinforcement Learning. CoRR (2016)
Tom Everitt, Marcus Hutter
Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search. Australasian Conference on Artificial Intelligence (2015)
Tom Everitt, Marcus Hutter
A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem. CoRR (2015)
Tom Everitt, Jan Leike, Marcus Hutter
Sequential Extensions of Causal and Evidential Decision Theory. CoRR (2015)
Tom Everitt, Marcus Hutter
Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search. Australasian Conference on Artificial Intelligence (2015)
Tom Everitt, Jan Leike, Marcus Hutter
Sequential Extensions of Causal and Evidential Decision Theory. ADT (2015)
Tom Everitt, Tor Lattimore, Marcus Hutter
Free Lunch for optimisation under the universal distribution. IEEE Congress on Evolutionary Computation (2014)
Tansu Alpcan, Tom Everitt, Marcus Hutter
Can we measure the difficulty of an optimization problem? ITW (2014)