עקוב אחר
Alex Vitvitskyi
Alex Vitvitskyi
DeepMind
כתובת אימייל מאומתת בדומיין google.com
כותרת
צוטט על ידי
צוטט על ידי
שנה
Agent57: Outperforming the atari human benchmark
AP Badia, B Piot, S Kapturowski, P Sprechmann, A Vitvitskyi, ZD Guo, ...
International conference on machine learning, 507-517, 2020
6912020
Never give up: Learning directed exploration strategies
AP Badia, P Sprechmann, A Vitvitskyi, D Guo, B Piot, S Kapturowski, ...
arXiv preprint arXiv:2002.06038, 2020
3642020
A generalist neural algorithmic learner
B Ibarz, V Kurin, G Papamakarios, K Nikiforou, M Bennani, R Csordás, ...
Learning on graphs conference, 2: 1-2: 23, 2022
652022
Beyond fine-tuning: Transferring behavior in reinforcement learning
V Campos, P Sprechmann, S Hansen, A Barreto, S Kapturowski, ...
arXiv preprint arXiv:2102.13515, 2021
302021
Transformers need glasses! Information over-squashing in language tasks
F Barbero, A Banino, S Kapturowski, D Kumaran, JGM Araújo, A Vitvitskyi, ...
arXiv preprint arXiv:2406.04267, 2024
102024
Coverage as a principle for discovering transferable behavior in reinforcement learning
V Campos, P Sprechmann, SS Hansen, A Barreto, C Blundell, A Vitvitskyi, ...
92021
Transformers meet Neural Algorithmic Reasoners
W Bounsi, B Ibarz, A Dudzik, JB Hamrick, L Markeeva, A Vitvitskyi, ...
arXiv preprint arXiv:2406.09308, 2024
42024
The CLRS-Text Algorithmic Reasoning Language Benchmark
L Markeeva, S McLeish, B Ibarz, W Bounsi, O Kozlova, A Vitvitskyi, ...
arXiv preprint arXiv:2406.04229, 2024
32024
Round and Round We Go! What makes Rotary Positional Encodings useful?
F Barbero, A Vitvitskyi, C Perivolaropoulos, R Pascanu, P Veličković
arXiv preprint arXiv:2410.06205, 2024
2024
Jointly learning exploratory and non-exploratory action selection policies
AP Badia, P Sprechmann, A Vitvitskyi, Z Guo, B Piot, SJ Kapturowski, ...
US Patent App. 18/334,112, 2024
2024
Jointly learning exploratory and non-exploratory action selection policies
AP Badia, P Sprechmann, A Vitvitskyi, Z Guo, B Piot, SJ Kapturowski, ...
US Patent 11,714,990, 2023
2023
Reinforcement learning with adaptive return computation schemes
AP Badia, B Piot, P Sprechmann, SJ Kapturowski, A Vitvitskyi, Z Guo, ...
US Patent App. 17/797,878, 2023
2023
המערכת אינה יכולה לבצע את הפעולה כעת. נסה שוב מאוחר יותר.
מאמרים 1–12