Ryan D'Orazio - RankMe

21 papers A* 7A 1Journal 13

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results. CoRR Francesco Orabona, Ryan D'Orazio
2025	A*	`conf`	Solving hidden monotone variational inequalities with surrogate losses. ICLR Ryan D'Orazio, Danilo Vucetic, Zichu Liu, Junhyung Lyle Kim, Ioannis Mitliagkas, Gauthier Gidel
2024	J	`jnl`	Solving Hidden Monotone Variational Inequalities with Surrogate Losses. CoRR Ryan D'Orazio, Danilo Vucetic, Zichu Liu, Junhyung Lyle Kim, Ioannis Mitliagkas, Gauthier Gidel
2023	A*	`conf`	A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games. ICLR Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer
2023	A*	`conf`	Abstracting Imperfect Information Away from Two-Player Zero-Sum Games. ICML Samuel Sokota, Ryan D'Orazio, Chun Kai Ling, David J. Wu, J. Zico Kolter, Noam Brown
2023	J	`jnl`	Abstracting Imperfect Information Away from Two-Player Zero-Sum Games. CoRR Samuel Sokota, Ryan D'Orazio, Chun Kai Ling, David J. Wu, J. Zico Kolter, Noam Brown
2023	J	`jnl`	Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize. Trans. Mach. Learn. Res. Ryan D'Orazio, Nicolas Loizou, Issam H. Laradji, Ioannis Mitliagkas
2022	J	`jnl`	A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games. CoRR Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer
2021	A*	`conf`	Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. ICML Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy R. Greenwald
2021	J	`jnl`	Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. CoRR Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy Greenwald
2021	A*	`conf`	Hindsight and Sequential Rationality of Correlated Play. AAAI Dustin Morrill, Ryan D'Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy R. Greenwald, Michael Bowling
2021	J	`jnl`	Optimistic and Adaptive Lagrangian Hedging. CoRR Ryan D'Orazio, Ruitong Huang
2021	A*	`conf`	Solving Common-Payoff Games with Approximate Policy Iteration. AAAI Samuel Sokota, Edward Lockhart, Finbarr Timbers, Elnaz Davoodi, Ryan D'Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot
2021	J	`jnl`	Solving Common-Payoff Games with Approximate Policy Iteration. CoRR Samuel Sokota, Edward Lockhart, Finbarr Timbers, Elnaz Davoodi, Ryan D'Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot
2021	J	`jnl`	Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize. CoRR Ryan D'Orazio, Nicolas Loizou, Issam H. Laradji, Ioannis Mitliagkas
2020	A	`conf`	Alternative Function Approximation Parameterizations for Solving Games: An Analysis of ƒ-Regression Counterfactual Regret Minimization. AAMAS Ryan D'Orazio, Dustin Morrill, James R. Wright, Michael Bowling
2020	J	`jnl`	Hindsight and Sequential Rationality of Correlated Play. CoRR Dustin Morrill, Ryan D'Orazio, Reca Sarfati, Marc Lanctot, James R. Wright, Amy Greenwald, Michael Bowling
2019	J	`jnl`	Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization. CoRR Ryan D'Orazio, Dustin Morrill, James R. Wright, Michael Bowling
2019	J	`jnl`	Bounds for Approximate Regret-Matching Algorithms. CoRR Ryan D'Orazio, Dustin Morrill, James R. Wright
2019	A*	`conf`	Simultaneous Prediction Intervals for Patient-Specific Survival Curves. IJCAI Samuel Sokota, Ryan D'Orazio, Khurram Javed, Humza Haider, Russell Greiner
2019	J	`jnl`	Simultaneous Prediction Intervals for Patient-Specific Survival Curves. CoRR Samuel Sokota, Ryan D'Orazio, Khurram Javed, Humza Haider, Russell Greiner