Obserwuj
Laurent Orseau
Laurent Orseau
Research Scientist at Google DeepMind
Zweryfikowany adres z google.com
Tytuł
Cytowane przez
Cytowane przez
Rok
AI safety gridworlds
J Leike, M Martic, V Krakovna, PA Ortega, T Everitt, A Lefrancq, L Orseau, ...
arXiv preprint arXiv:1711.09883, 2017
3282017
Safely Interruptible Agents
L Orseau, S Armstrong
Uncertainty in Artificial Intelligence, 557–566, 2016
1522016
Reinforcement learning with a corrupted reward channel
T Everitt, V Krakovna, L Orseau, M Hutter, S Legg
arXiv preprint arXiv:1705.08417, 2017
1212017
Delusion, survival, and intelligent agents
M Ring, L Orseau
Artificial General Intelligence: 4th International Conference, AGI 2011 …, 2011
942011
Logarithmic pruning is all you need
L Orseau, M Hutter, O Rivasplata
Advances in Neural Information Processing Systems 33, 2925-2934, 2020
912020
An investigation of model-free planning
A Guez, M Mirza, K Gregor, R Kabra, S Racanière, T Weber, D Raposo, ...
International conference on machine learning, 2464-2473, 2019
902019
Goal misgeneralization in deep reinforcement learning
LL Di Langosco, J Koch, LD Sharkey, J Pfau, D Krueger
International Conference on Machine Learning, 12004-12019, 2022
772022
Language modeling is compression
G Delétang, A Ruoss, PA Duquenne, E Catt, T Genewein, C Mattern, ...
arXiv preprint arXiv:2309.10668, 2023
602023
Penalizing side effects using stepwise relative reachability
V Krakovna, L Orseau, R Kumar, M Martic, S Legg
arXiv preprint arXiv:1806.01186, 2018
562018
Space-Time Embedded Intelligence
L Orseau, M Ring
Artificial General Intelligence, 209-218, 2012
522012
Universal knowledge-seeking agents for stochastic environments
L Orseau, T Lattimore, M Hutter
Algorithmic Learning Theory: 24th International Conference, ALT 2013 …, 2013
512013
Thompson sampling is asymptotically optimal in general environments
J Leike, T Lattimore, L Orseau, M Hutter
arXiv preprint arXiv:1602.07905, 2016
442016
Self-modification and mortality in artificial agents
L Orseau, M Ring
Artificial General Intelligence: 4th International Conference, AGI 2011 …, 2011
442011
Avoiding side effects by considering future tasks
V Krakovna, L Orseau, R Ngo, M Martic, S Legg
Advances in Neural Information Processing Systems 33, 19064-19074, 2020
422020
Single-agent policy tree search with guarantees
L Orseau, L Lelis, T Lattimore, T Weber
Advances in Neural Information Processing Systems 31, 2018
402018
Universal knowledge-seeking agents
L Orseau
Theoretical Computer Science 519, 127-139, 2014
302014
Soft-bayes: Prod for mixtures of experts with log-loss
L Orseau, T Lattimore, S Legg
International Conference on Algorithmic Learning Theory, 372-399, 2017
282017
Optimality issues of universal greedy agents with static priors
L Orseau
Algorithmic Learning Theory: 21st International Conference, ALT 2010 …, 2010
252010
Pitfalls of learning a reward function online
S Armstrong, J Leike, L Orseau, S Legg
arXiv preprint arXiv:2004.13654, 2020
232020
Policy-guided heuristic search with guarantees
L Orseau, LHS Lelis
Proceedings of the AAAI Conference on Artificial Intelligence 35 (14), 12382 …, 2021
212021
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20