Следене
Michael K Cohen
Michael K Cohen
Postdoc, UC Berkeley
Потвърден имейл адрес: berkeley.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
Advanced artificial agents intervene in the provision of reward
MK Cohen, M Hutter, MA Osborne
AI magazine 43 (3), 282-293, 2022
462022
Asymptotically unambitious artificial general intelligence
MK Cohen, B Vellambi, M Hutter
Proceedings of the AAAI Conference on Artificial Intelligence 34 (03), 2467-2476, 2020
212020
Regulating advanced artificial agents
MK Cohen, N Kolt, Y Bengio, GK Hadfield, S Russell
Science 384 (6691), 36-38, 2024
162024
A strongly asymptotically optimal agent in general environments
MK Cohen, E Catt, M Hutter
arXiv preprint arXiv:1903.01021, 2019
132019
Pessimism about unknown unknowns inspires conservatism
MK Cohen, M Hutter
Conference on learning theory, 1344-1373, 2020
112020
Conference on learning theory
MK Cohen, M Hutter
82020
Log-Linear-Time Gaussian Processes Using Binary Tree Kernels
MK Cohen, S Daulton, MA Osborne
Advances in Neural Information Processing Systems 35, 8118-8129, 2022
62022
Fully general online imitation learning
MK Cohen, M Hutter, N Nanda
Journal of Machine Learning Research 23 (334), 1-30, 2022
32022
Curiosity killed or incapacitated the cat and the asymptotically optimal agent
MK Cohen, E Catt, M Hutter
IEEE Journal on Selected Areas in Information Theory 2 (2), 665-677, 2021
32021
Intelligence and unambitiousness using algorithmic information theory
MK Cohen, B Vellambi, M Hutter
IEEE Journal on Selected Areas in Information Theory 2 (2), 678-690, 2021
22021
Strong Asymptotic Optimality in General Environments
MK Cohen, E Catt, M Hutter
arXiv preprint arXiv:1903.01021, 2019
12019
Can a Bayesian Oracle Prevent Harm from an Agent?
Y Bengio, MK Cohen, N Malkin, M MacDermott, D Fornasiere, P Greiner, ...
arXiv preprint arXiv:2408.05284, 2024
2024
Pessimistic Bayesianism for conservative optimization and imitation
M Cohen
University of Oxford, 2023
2023
Intra-feature Random Forest Clustering
M Cohen
Machine Learning, Optimization, and Big Data: Third International Conference …, 2018
2018
Don’t do anything I’d never do? KL regularization to an imitative “base model” does not implement this
MK Cohen, M Hutter, Y Bengio, S Russell
Imitation Learning is Probably Existentially Safe
MK Cohen, M Hutter
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–16