Victoria Krakovna

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 19

Top Topics

Tamper Detection

Unsupervised Grammar Induction

Artificial Agents

Top Venues

Publications

Iason Gabriel, Arianna Manzini, Geoff Keeling, Lisa Anne Hendricks, Verena Rieser, Hasan Iqbal, Nenad Tomasev, Ira Ktena, Zachary Kenton, Mikel Rodriguez, Seliem El-Sayed, Sasha Brown, Canfer Akbulut, Andrew Trask, Edward Hughes, A. Stevie Bergman, Renee Shelby, Nahema Marchal, Conor Griffin, Juan Mateos-Garcia, Laura Weidinger, Winnie Street, Benjamin Lange, Alex Ingerman, Alison Lentz, Reed Enger, Andrew Barakat, Victoria Krakovna, John Oliver Siy, Zeb Kurth-Nelson, Amanda McCroskery, Vijay Bolina, Harry Law, Murray Shanahan, Lize Alberts, Borja Balle, Sarah de Haas, Yetunde Ibitoye, Allan Dafoe, Beth Goldberg, Sébastien Krier, Alexander Reese, Sims Witherspoon, Will Hawkins, Maribeth Rauh, Don Wallace, Matija Franklin, Josh A. Goldstein, Joel Lehman, Michael Klenk, Shannon Vallor, Courtney Biles, Meredith Ringel Morris, Helen King, Blaise Agüera y Arcas, William Isaac, James Manyika
The Ethics of Advanced AI Assistants. CoRR (2024)
Evan Ryan Gunter, Yevgeny Liokumovich, Victoria Krakovna
Quantifying stability of non-power-seeking in artificial agents. CoRR (2024)
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane
Evaluating Frontier Models for Dangerous Capabilities. CoRR (2024)
Raymond Douglas, Jacek Karwowski, Chan Bae, Andis Draguns, Victoria Krakovna
Limitations of Agents Simulated by Predictive Models. CoRR (2024)
Victoria Krakovna, János Kramár
Power-seeking can be probable and predictive for trained agents. CoRR (2023)
Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, Zac Kenton
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals. CoRR (2022)
Tom Everitt, Marcus Hutter, Ramana Kumar, Victoria Krakovna
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective. Synth. 198 (27) (2021)
Victoria Krakovna, Laurent Orseau, Richard Ngo, Miljan Martic, Shane Legg
Avoiding Side Effects By Considering Future Tasks. CoRR (2020)
Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, Shane Legg
REALab: An Embedded Perspective on Tampering. CoRR (2020)
Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg
Avoiding Tampering Incentives in Deep RL via Decoupled Approval. CoRR (2020)
Victoria Krakovna, Laurent Orseau, Richard Ngo, Miljan Martic, Shane Legg
Avoiding Side Effects By Considering Future Tasks. NeurIPS (2020)
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
Modeling AGI Safety Frameworks with Causal Influence Diagrams. CoRR (2019)
Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
Modeling AGI Safety Frameworks with Causal Influence Diagrams. AISafety@IJCAI (2019)
Victoria Krakovna, Laurent Orseau, Miljan Martic, Shane Legg
Penalizing Side Effects using Stepwise Relative Reachability. AISafety@IJCAI (2019)
Victoria Krakovna, Laurent Orseau, Miljan Martic, Shane Legg
Measuring and avoiding side effects using relative reachability. CoRR (2018)
Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg
AI Safety Gridworlds. CoRR (2017)
Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg
Reinforcement Learning with a Corrupted Reward Channel. CoRR (2017)
Tom Everitt, Victoria Krakovna, Laurent Orseau, Shane Legg
Reinforcement Learning with a Corrupted Reward Channel. IJCAI (2017)
Cory Shain, William Bryce, Lifeng Jin, Victoria Krakovna, Finale Doshi-Velez, Timothy A. Miller, William Schuler, Lane Schwartz
Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input. COLING (2016)
Matthew Skala, Victoria Krakovna, János Kramár, Gerald Penn
A Generalized-Zero-Preserving Method for Compact Encoding of Concept Lattices. ACL (2010)