עקוב אחר
Tom Everitt
Tom Everitt
Staff Research Scientist at Google DeepMind
כתובת אימייל מאומתת בדומיין google.com - דף הבית
כותרת
צוטט על ידי
צוטט על ידי
שנה
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
3792018
AI safety gridworlds‏
J Leike, M Martic, V Krakovna, PA Ortega, T Everitt, A Lefrancq, L Orseau, ...‏
arXiv preprint arXiv:1711.09883, 2017‏
3622017
Alignment of language agents‏
Z Kenton, T Everitt, L Weidinger, I Gabriel, V Mikulik, G Irving‏
arXiv preprint arXiv:2103.14659, 2021‏
1672021
AGI safety literature review‏
T Everitt, G Lea, M Hutter‏
International Joint Conference on AI (IJCAI), 2018‏
1602018
Count-based exploration in feature space for reinforcement learning‏
J Martin, SN Sasikumar, T Everitt, M Hutter‏
International Joint Conference on AI (IJCAI), 2017‏
1512017
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
1312017
Specification gaming: the flip side of AI ingenuity‏
V Krakovna, J Uesato, V Mikulik, M Rahtz, T Everitt, R Kumar, Z Kenton, ...‏
DeepMind Blog 3, 2020‏
1232020
Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective‏
T Everitt, M Hutter, R Kumar, V Krakovna‏
Synthese, 2021‏
1042021
Shaking the foundations: delusions in sequence models for interaction and control‏
PA Ortega, M Kunesch, G Delétang, T Genewein, J Grau-Moya, J Veness, ...‏
arXiv preprint arXiv:2110.10819, 2021‏
652021
Agent incentives: A causal perspective‏
T Everitt, R Carey, ED Langlois, PA Ortega, S Legg‏
Proceedings of the AAAI Conference on Artificial Intelligence 35 (13), 11487 …, 2021‏
592021
Avoiding wireheading with value reinforcement learning‏
T Everitt, M Hutter‏
International Conference on Artificial General Intelligence (AGI), 12-22, 2016‏
532016
Towards safe artificial general intelligence‏
T Everitt‏
PQDT-Global, 2019‏
412019
Robust agents learn causal world models‏
J Richens, T Everitt‏
The Twelfth International Conference on Learning Representations, 2024‏
392024
Discovering agents‏
Z Kenton, R Kumar, S Farquhar, J Richens, M MacDermott, T Everitt‏
Artificial Intelligence 322, 103963, 2023‏
382023
Universal artificial intelligence: Practical agents and fundamental challenges‏
T Everitt, M Hutter‏
Foundations of trusted autonomy, 15-46, 2018‏
362018
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
332019
Self-modification of policy and utility function in rational agents‏
T Everitt, D Filan, M Daswani, M Hutter‏
International Conference on Artificial General Intelligence (AGI), 1-11, 2016‏
332016
Honesty is the best policy: defining and mitigating AI deception‏
F Ward, F Toni, F Belardinelli, T Everitt‏
Advances in neural information processing systems 36, 2313-2341, 2023‏
302023
Path-specific objectives for safer agent incentives‏
S Farquhar, R Carey, T Everitt‏
Proceedings of the AAAI Conference on Artificial Intelligence 36 (9), 9529-9538, 2022‏
292022
A game-theoretic analysis of the off-switch game‏
T Wängberg, M Böörs, E Catt, T Everitt, M Hutter‏
Artificial General Intelligence: 10th International Conference, AGI 2017 …, 2017‏
272017
המערכת אינה יכולה לבצע את הפעולה כעת. נסה שוב מאוחר יותר.
מאמרים 1–20