A unified approach to reinforcement learning, quantal response equilibria, and two-player zero-sum games S Sokota, R D'Orazio, JZ Kolter, N Loizou, M Lanctot, I Mitliagkas, ...
arXiv preprint arXiv:2206.05825, 2022
62 2022 Hindsight and sequential rationality of correlated play D Morrill, R D'Orazio, R Sarfati, M Lanctot, JR Wright, AR Greenwald, ...
Proceedings of the AAAI Conference on Artificial Intelligence 35 (6), 5584-5594, 2021
42 2021 Efficient deviation types and learning for hindsight rationality in extensive-form games D Morrill, R D’Orazio, M Lanctot, JR Wright, M Bowling, AR Greenwald
International Conference on Machine Learning, 7818-7828, 2021
38 2021 Stochastic mirror descent: Convergence analysis and adaptive variants via the mirror stochastic polyak stepsize R D'Orazio, N Loizou, I Laradji, I Mitliagkas
arXiv preprint arXiv:2110.15412, 2021
35 2021 Solving common-payoff games with approximate policy iteration S Sokota, E Lockhart, F Timbers, E Davoodi, R D'Orazio, N Burch, ...
Proceedings of the AAAI Conference on Artificial Intelligence 35 (11), 9695-9703, 2021
18 2021 Alternative Function Approximation Parameterizations for Solving Games: An Analysis of R D'Orazio, D Morrill, JR Wright, M Bowling
arXiv preprint arXiv:1912.02967, 2019
11 2019 Abstracting imperfect information away from two-player zero-sum games S Sokota, R D’Orazio, CK Ling, DJ Wu, JZ Kolter, N Brown
International Conference on Machine Learning, 32169-32193, 2023
8 2023 Simultaneous prediction intervals for patient-specific survival curves S Sokota, R D'Orazio, K Javed, H Haider, R Greiner
arXiv preprint arXiv:1906.10780, 2019
8 2019 Regret minimization with function approximation in extensive-form games R D'Orazio
6 2020 Optimistic and adaptive lagrangian hedging R D'Orazio, R Huang
arXiv preprint arXiv:2101.09603, 2021
5 2021 On stochastic mirror descent: Convergence analysis and adaptive variants R D’Orazio, N Loizou, I Laradji, I Mitliagkas
Beyond First-Order Methods in ML Systems Workshop, Int. Conf. Machine Learning, 2021
3 2021 Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections D Morrill, R D'Orazio, M Lanctot, JR Wright, M Bowling, AR Greenwald
arXiv preprint arXiv:2205.12031, 2022
1 2022 Bounds for approximate regret-matching algorithms R D'Orazio, D Morrill, JR Wright
arXiv preprint arXiv:1910.01706, 2019
1 2019 Solving hidden monotone variational inequalities with surrogate losses R D'Orazio, D Vucetic, Z Liu, JL Kim, I Mitliagkas, G Gidel
arXiv preprint arXiv:2411.05228, 2024
2024 Alternative Function Approximation Parameterizations for Solving Games R D’Orazio, D Morrill, JR Wright, M Bowling
Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games Supplementary D Morrill, R D’Orazio, M Lanctot, JR Wright, M Bowling, AR Greenwald
Marc LanctotResearch Scientist, Google DeepMindE-mail megerősítve itt: google.com