Victoria (Viktoriya) Krakovna
Victoria (Viktoriya) Krakovna
Senior Research Scientist at DeepMind
Verified email at - Homepage
Cited by
Cited by
AI safety gridworlds
J Leike, M Martic, V Krakovna, PA Ortega, T Everitt, A Lefrancq, L Orseau, ...
arXiv preprint arXiv:1711.09883, 2017
Reinforcement Learning with a Corrupted Reward Channel
T Everitt, V Krakovna, L Orseau, M Hutter, S Legg
IJCAI AI & Autonomy, 2017
Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models
V Krakovna, F Doshi-Velez
ICML Workshop on Human Interpretability (WHI 2016), arXiv preprint arXiv …, 2016
Penalizing side effects using stepwise relative reachability
V Krakovna, L Orseau, R Kumar, M Martic, S Legg
arXiv preprint arXiv:1806.01186, 2018
Measuring and avoiding side effects using relative reachability
V Krakovna, L Orseau, M Martic, S Legg
arXiv preprint arXiv:1806.01186, 2018
Specification gaming examples in AI
V Krakovna, 2018
Modeling AGI safety frameworks with causal influence diagrams
T Everitt, R Kumar, V Krakovna, S Legg
arXiv preprint arXiv:1906.08663, 2019
A generalized-zero-preserving method for compact encoding of concept lattices
M Skala, V Krakovna, J Kramár, G Penn
Proceedings of the 48th annual meeting of the Association for Computational …, 2010
Interpretable selection and visualization of features and interactions using bayesian forests
V Krakovna, J Du, JS Liu
Statistics and its Interface 2018 (Volume 11 Number 3), arXiv preprint arXiv …, 2015
Building interpretable models: From Bayesian networks to neural networks
V Krakovna
A Minimalistic Approach to Sum-Product Network Learning for Real Applications
V Krakovna, M Looks
ICLR 2016 workshop, arXiv preprint arXiv:1602.04259, 2016
Avoiding Side Effects By Considering Future Tasks
V Krakovna, L Orseau, R Ngo, M Martic, S Legg
NeurIPS 2020, arXiv preprint arXiv:2010.07877, 2020
The system can't perform the operation now. Try again later.
Articles 1–12