List of Publications
| [HFE+21] |
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, and Michael
Wooldridge.
Equilibrium refinements for multi-agent influence diagrams: Theory
and practice.
In AAMAS, 2021. [ bib | arXiv | Abstract ] |
| [ECL+21] |
Tom Everitt, Ryan Carey, Eric Langlois, Pedro A Ortega, and Shane Legg.
Agent incentives: A causal perspective.
In AAAI, 2021. [ bib | arXiv | Abstract ] |
| [LE21] |
Eric Langlois and Tom Everitt.
How RL agents behave when their actions are modified.
In AAAI, 2021. [ bib | arXiv | Abstract ] |
| [EHKK21] |
Tom Everitt, Marcus Hutter, Ramana Kumar, and Victoria Krakovna.
Reward tampering problems and solutions in reinforcement learning: A
causal influence diagram perspective.
Synthese, 2021. [ bib | arXiv | Abstract ] |
| [KUN+20] |
Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, and
Shane Legg.
REALab: An embedded perspective on tampering, 2020. [ bib | arXiv | Abstract ] |
| [UKK+20] |
Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, and
Shane Legg.
Avoiding tampering incentives in deep RL via decoupled approval,
2020. [ bib | arXiv | Abstract ] |
| [CLEL20] |
Ryan Carey, Eric Langlois, Tom Everitt, and Shane Legg.
The incentives that shape behavior, 2020.
presented at the SafeAI AAAI workshop. [ bib | arXiv | Abstract ] |
| [EKKL19] |
Tom Everitt, Ramana Kumar, Victoria Krakovna, and Shane Legg.
Modeling AGI safety frameworks with causal influence diagrams.
In IJCAI AI Safety Workshop, 2019. [ bib | arXiv | Abstract ] |
| [EOBL19] |
Tom Everitt, Pedro A Ortega, Elizabeth Barnes, and Shane Legg.
Understanding agent incentives using causal influence diagrams. Part
I: Single action settings, 2019. [ bib | arXiv | Abstract ] |
| [LKE+18] |
Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, and Shane
Legg.
Scalable agent alignment via reward modeling: a research direction,
2018. [ bib | arXiv | Abstract ] |
| [Eve18] |
Tom Everitt.
Towards Safe Artificial General Intelligence.
PhD thesis, Australian National University, May 2018. [ bib | http | Abstract ] |
| [EH18a] |
Tom Everitt and Marcus Hutter.
The alignment problem for Bayesian history-based reinforcement
learners.
Technical report, 2018.
Winner of the AI Alignment Prize. [ bib | .pdf | Abstract ] |
| [ELH18] |
Tom Everitt, Gary Lea, and Marcus Hutter.
AGI safety literature review.
In International Joint Conference on AI (IJCAI), 2018. [ bib | arXiv | http | Abstract ] |
| [EH18b] |
Tom Everitt and Marcus Hutter.
Universal artificial intelligence: Practical agents and fundamental
challengs.
In Hussein A. Abbass, Jason Scholz, and Darryn J. Reid, editors,
Foundations of Trusted Autonomy, Studies in Systems, Decision and Control,
chapter 2, pages 15--46. Springer, 2018. [ bib | DOI | http | Abstract ] |
| [LMK+17] |
Jan Leike, Miljan Martic, Victoria Krakovna, Pedro Ortega, Tom
Everitt, Andrew Lefrancq, Laurent Orseau, and Shane Legg.
AI Safety Gridworlds.
ArXiv e-prints, November 2017. [ bib | arXiv | Abstract ] |
| [EKO+17] |
Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, and Shane Legg.
Reinforcement learning with a corrupted reward signal.
In Proceedings of the Twenty-Sixth International Joint
Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia,
August 19-26, 2017, pages 4705--4713, 2017. [ bib | DOI | arXiv | www: | Abstract ] |
| [MNSEH17] |
Jarryd Martin, Suraj Narayanan S, Tom Everitt, and Marcus Hutter.
Count-based exploration in feature space for reinforcement learning.
In Proceedings of the Twenty-Sixth International Joint
Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia,
August 19-26, 2017, pages 2471--2478, 2017. [ bib | DOI | arXiv | www: | Abstract ] |
| [WBC+17] |
Tobias Wängberg, Mikael Böörs, Elliot Catt, Tom Everitt, and Marcus
Hutter.
A game-theoretic analysis of the off-switch game.
In Tom Everitt, Ben Goertzel, and Alexey Potapov, editors,
Artificial General Intelligence: 10th International Conference, AGI 2017,
Melbourne, VIC, Australia, August 15-18, 2017, Proceedings, pages 167--177,
Cham, 2017. Springer International Publishing. [ bib | DOI | arXiv | http | Abstract ] |
| [EGP17] |
Tom Everitt, Ben Goertzel, and Alexey Potapov, editors.
Artificial General Intelligence: 10th International Conference,
AGI 2017, Melbourne, VIC, Australia, August 15-18, 2017, Proceedings.
Springer International Publishing, Cham, 2017. [ bib | DOI | http ] |
| [EFDH16] |
Tom Everitt, Daniel Filan, Mayank Daswani, and Marcus Hutter.
Self-modification of policy and utility function in rational agents.
In Bas Steunebrink, Pei Wang, and Ben Goertzel, editors,
Artificial General Intelligence: 9th International Conference, AGI 2016, New
York, NY, USA, July 16-19, 2016, Proceedings, pages 1--11, Cham, 2016.
Springer International Publishing. [ bib | DOI | arXiv | Abstract ] |
| [EH16] |
Tom Everitt and Marcus Hutter.
Avoiding wireheading with value reinforcement learning.
In Bas Steunebrink, Pei Wang, and Ben Goertzel, editors,
Artificial General Intelligence: 9th International Conference, AGI 2016, New
York, NY, USA, July 16-19, 2016, Proceedings, pages 12--22, Cham, 2016.
Springer International Publishing.
Source
code. [ bib | DOI | arXiv | Abstract ] |
| [MEH16] |
Jarryd Martin, Tom Everitt, and Marcus Hutter.
Death and suicide in universal artificial intelligence.
In Bas Steunebrink, Pei Wang, and Ben Goertzel, editors,
Artificial General Intelligence: 9th International Conference, AGI 2016, New
York, NY, USA, July 16-19, 2016, Proceedings, pages 23--32, Cham, 2016.
Springer International Publishing. [ bib | DOI | arXiv | Abstract ] |
| [ELH15] |
Tom Everitt, Jan Leike, and Marcus Hutter.
Sequential extensions of causal and evidential decision theory.
In Toby Walsh, editor, Algorithmic Decision Theory: 4th
International Conference, ADT 2015, Lexington, KY, USA, September 27-30,
2015, Proceedings, pages 205--221, Cham, 2015. Springer International
Publishing.
Source
code. [ bib | DOI | arXiv | Abstract ] |
| [EH15a] |
Tom Everitt and Marcus Hutter.
Analytical results on the BFS vs. DFS algorithm selection
problem. Part I: Tree search.
In Bernhard Pfahringer and Jochen Renz, editors, AI 2015:
Advances in Artificial Intelligence: 28th Australasian Joint Conference,
Canberra, ACT, Australia, November 30 -- December 4, 2015, Proceedings,
pages 157--165, Cham, 2015. Springer International Publishing.
Source
code. [ bib | DOI | Abstract ] |
| [EH15b] |
Tom Everitt and Marcus Hutter.
Analytical results on the BFS vs. DFS algorithm selection
problem. Part II: Graph search.
In Bernhard Pfahringer and Jochen Renz, editors, AI 2015:
Advances in Artificial Intelligence: 28th Australasian Joint Conference,
Canberra, ACT, Australia, November 30 -- December 4, 2015, Proceedings,
pages 166--178, Cham, 2015. Springer International Publishing.
Source
code. [ bib | DOI | Abstract ] |
| [EH15c] |
Tom Everitt and Marcus Hutter.
A topological approach to meta-heuristics: Analytical results on the
BFS vs. DFS algorithm selection problem.
Technical report, Australian National University, 2015. [ bib | arXiv | Abstract ] |
| [ELH14] |
T. Everitt, T. Lattimore, and M. Hutter.
Free lunch for optimisation under the universal distribution.
In 2014 IEEE Congress on Evolutionary Computation (CEC), pages
167--174, July 2014. [ bib | DOI | arXiv | Abstract ] |
| [AEH14] |
T. Alpcan, T. Everitt, and M. Hutter.
Can we measure the difficulty of an optimization problem?
In Information Theory Workshop (ITW), 2014 IEEE, pages
356--360, Nov 2014. [ bib | DOI | .pdf | Abstract ] |
| [Eve13] |
Tom Everitt.
Universal induction and optimisation: No free lunch?
MSc thesis, Stockholm University, 2013. [ bib | .pdf | Abstract ] |
| [Eve10] |
Tom Everitt.
Automated Theorem Proving.
BSc thesis, Stockholm University, 2010. [ bib | .pdf | Abstract ] |
This file was generated by bibtex2html 1.99.