Tom Everitt
Tom Everitt
Research Scientist at Deepmind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
AI safety gridworlds
J Leike, M Martic, V Krakovna, PA Ortega, T Everitt, A Lefrancq, L Orseau, ...
arXiv preprint arXiv:1711.09883, 2017
1662017
Reinforcement Learning with Corrupted Reward Channel
T Everitt, V Krakovna, L Orseau, M Hutter, S Legg
26th International Joint Conference on Artificial Intelligence (IJCAI), 2017
572017
AGI safety literature review
T Everitt, G Lea, M Hutter
arXiv preprint arXiv:1805.01109, 2018
562018
Scalable agent alignment via reward modeling: a research direction
J Leike, D Krueger, T Everitt, M Martic, V Maini, S Legg
arXiv preprint arXiv:1811.07871, 2018
522018
Count-based exploration in feature space for reinforcement learning
J Martin, SN Sasikumar, T Everitt, M Hutter
arXiv preprint arXiv:1706.08090, 2017
452017
Avoiding wireheading with value reinforcement learning
T Everitt, M Hutter
International Conference on Artificial General Intelligence, 12-22, 2016
312016
Self-modification of policy and utility function in rational agents
T Everitt, D Filan, M Daswani, M Hutter
International Conference on Artificial General Intelligence, 1-11, 2016
242016
Towards safe artificial general intelligence
T Everitt
The Australian National University, 2018
192018
Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
T Everitt, PA Ortega, E Barnes, S Legg
arXiv preprint arXiv:1902.09980, 2019
162019
Universal artificial intelligence
T Everitt, M Hutter
Foundations of Trusted Autonomy, 15-46, 2018
142018
Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective
T Everitt, M Hutter
arXiv preprint arXiv:1908.04734, 2019
122019
Modeling AGI safety frameworks with causal influence diagrams
T Everitt, R Kumar, V Krakovna, S Legg
arXiv preprint arXiv:1906.08663, 2019
112019
Death and suicide in universal artificial intelligence
J Martin, T Everitt, M Hutter
International Conference on Artificial General Intelligence, 23-32, 2016
112016
Analytical results on the BFS vs. DFS algorithm selection problem. Part I: tree search
T Everitt, M Hutter
Australasian Joint Conference on Artificial Intelligence, 157-165, 2015
112015
Sequential extensions of causal and evidential decision theory
T Everitt, J Leike, M Hutter
International Conference on Algorithmic DecisionTheory, 205-221, 2015
112015
Free lunch for optimisation under the universal distribution
T Everitt, T Lattimore, M Hutter
2014 IEEE Congress on Evolutionary Computation (CEC), 167-174, 2014
112014
Can we measure the difficulty of an optimization problem?
T Alpcan, T Everitt, M Hutter
2014 IEEE Information Theory Workshop (ITW 2014), 356-360, 2014
92014
Specification gaming: the flip side of AI ingenuity
V Krakovna, J Uesato, V Mikulik, M Rahtz, T Everitt, R Kumar, Z Kenton, ...
DeepMind Blog, 2020
82020
The alignment problem for Bayesian history-based reinforcement learners
T Everitt, M Hutter
Under submission, 2018
82018
Artificial general intelligence
T Everitt, B Goertzel, A Potapov
Lecture Notes in Artificial Intelligence. Heidelberg: Springer, 2017
82017
The system can't perform the operation now. Try again later.
Articles 1–20