Zobrazeno 1 - 10
of 243
pro vyhledávání: '"P. Graepel"'
We show how the quality of decisions based on the aggregated opinions of the crowd can be conveniently studied using a sample of individual responses to a standard IQ questionnaire. We aggregated the responses to the IQ questionnaire using simple maj
Externí odkaz:
http://arxiv.org/abs/2410.10004
Autor:
Wu, Yan, Wershof, Esther, Schmon, Sebastian M, Nassar, Marcel, Osiński, Błażej, Eksi, Ridvan, Zhang, Kun, Graepel, Thore
We present a comprehensive framework for predicting the effects of perturbations in single cells, designed to standardize benchmarking in this rapidly evolving field. Our framework, PerturBench, includes a user-friendly platform, diverse datasets, me
Externí odkaz:
http://arxiv.org/abs/2408.10609
Autor:
Mohamad Bydon, Wenchun Qu, F. M. Moinuddin, Christine L. Hunt, Kristin L. Garlanger, Ronald K. Reeves, Anthony J. Windebank, Kristin D. Zhao, Ryan Jarrah, Brandon C. Trammell, Sally El Sammak, Giorgos D. Michalopoulos, Konstantinos Katsos, Stephen P. Graepel, Kimberly L. Seidel-Miller, Lisa A. Beck, Ruple S. Laughlin, Allan B. Dietz
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-3 (2024)
Externí odkaz:
https://doaj.org/article/296a648e5b93480eb9ccacd2491a8ea0
Autor:
Marris, Luke, Lanctot, Marc, Gemp, Ian, Omidshafiei, Shayegan, McAleer, Stephen, Connor, Jerome, Tuyls, Karl, Graepel, Thore
Rating strategies in a game is an important area of research in game theory and artificial intelligence, and can be applied to any real-world competitive or cooperative setting. Traditionally, only transitive dependencies between strategies have been
Externí odkaz:
http://arxiv.org/abs/2210.02205
Autor:
Mohamad Bydon, Wenchun Qu, F. M. Moinuddin, Christine L. Hunt, Kristin L. Garlanger, Ronald K. Reeves, Anthony J. Windebank, Kristin D. Zhao, Ryan Jarrah, Brandon C. Trammell, Sally El Sammak, Giorgos D. Michalopoulos, Konstantinos Katsos, Stephen P. Graepel, Kimberly L. Seidel-Miller, Lisa A. Beck, Ruple S. Laughlin, Allan B. Dietz
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-11 (2024)
Abstract Intrathecal delivery of autologous culture-expanded adipose tissue-derived mesenchymal stem cells (AD-MSC) could be utilized to treat traumatic spinal cord injury (SCI). This Phase I trial (ClinicalTrials.gov: NCT03308565) included 10 patien
Externí odkaz:
https://doaj.org/article/58b0acd07326464a9f8c65e7ce63ed73
Learning in strategy games (e.g. StarCraft, poker) requires the discovery of diverse policies. This is often achieved by iteratively training new policies against existing ones, growing a policy population that is robust to exploit. This iterative ap
Externí odkaz:
http://arxiv.org/abs/2202.07415
Autor:
Kopparapu, Kavya, Duéñez-Guzmán, Edgar A., Matyas, Jayd, Vezhnevets, Alexander Sasha, Agapiou, John P., McKee, Kevin R., Everett, Richard, Marecki, Janusz, Leibo, Joel Z., Graepel, Thore
A key challenge in the study of multiagent cooperation is the need for individual agents not only to cooperate effectively, but to decide with whom to cooperate. This is particularly critical in situations when other agents have hidden, possibly misa
Externí odkaz:
http://arxiv.org/abs/2201.01816
Autor:
Graepel, Thore, Herbrich, Ralf
Abstract We present PAC-Bayesian bounds for the generalisation error of the K-nearest-neighbour classifier (K-NN). This is achieved by casting the K-NN classifier into a kernel space framework in the limit of vanishing kernel bandwidth. We establish
Externí odkaz:
http://arxiv.org/abs/2109.13889
Autor:
Leibo, Joel Z., Duéñez-Guzmán, Edgar, Vezhnevets, Alexander Sasha, Agapiou, John P., Sunehag, Peter, Koster, Raphael, Matyas, Jayd, Beattie, Charles, Mordatch, Igor, Graepel, Thore
Publikováno v:
In International Conference on Machine Learning 2021 (pp. 6187-6199). PMLR
Existing evaluation suites for multi-agent reinforcement learning (MARL) do not assess generalization to novel situations as their primary objective (unlike supervised-learning benchmarks). Our contribution, Melting Pot, is a MARL evaluation suite th
Externí odkaz:
http://arxiv.org/abs/2107.06857
Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensiv
Externí odkaz:
http://arxiv.org/abs/2106.09435