Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
Dylan Foster
Principal Researcher
Publications
Publications by Year
-
The Power of Resets in Online Reinforcement Learning
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
NeurIPS 2024 | October 2024
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Dylan Foster, Adam Block, Dipendra Misra
NeurIPS 2024 | July 2024
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
NeurIPS 2024 | May 2024
Online Estimation via Offline Estimation: An Information-Theoretic Framework
Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
NeurIPS 2024 | April 2024
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
Harnessing Density Ratios for Online Reinforcement Learning
P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
ICLR 2024 | January 2024
-
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
2023 Conference on Learning Theory | July 2023
Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
Andrew Wagenmaker, Dylan Foster
2023 Conference on Learning Theory | July 2023
Minimax Rates for Conditional Density Estimation via Empirical Entropy
Blair Bilodeau, Dylan Foster, Daniel M. Roy
Annals of Statistics | July 2023
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
2023 Conference on Learning Theory | July 2023
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
Dylan Foster, Noah Golowich, Yanjun Han
2023 Conference on Learning Theory | July 2023
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
Dylan Foster, Noah Golowich, Sham M. Kakade
ICML 2023 | June 2023
The Role of Coverage in Online Reinforcement Learning
Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
2023 International Conference on Learning Representations | May 2023
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
ICML 2023 | April 2023
-
Interaction-Grounded Learning with Action-Inclusive Feedback
Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
NeurIPS 2022 | November 2022
On the Complexity of Adversarial Decision Making
Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
NeurIPS 2022 | November 2022
Oral presentation
Understanding the Eluder Dimension
Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
2022 Neural Information Processing Systems | October 2022
Contextual Bandits with Large Action Spaces: Made Practical
Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
2022 International Conference on Machine Learning | July 2022
Lower Bounds for Non-Convex Stochastic Optimization
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
Mathematical Programming | May 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
2022 Conference on Learning Theory | May 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022 Conference on Learning Theory | May 2022
-
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
2021 Conference on Learning Theory | July 2021
Publications by Research Area
-
The Power of Resets in Online Reinforcement Learning
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
NeurIPS 2024 | October 2024
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Dylan Foster, Adam Block, Dipendra Misra
NeurIPS 2024 | July 2024
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
NeurIPS 2024 | May 2024
Online Estimation via Offline Estimation: An Information-Theoretic Framework
Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
NeurIPS 2024 | April 2024
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
Harnessing Density Ratios for Online Reinforcement Learning
P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
ICLR 2024 | January 2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
Minimax Rates for Conditional Density Estimation via Empirical Entropy
Blair Bilodeau, Dylan Foster, Daniel M. Roy
Annals of Statistics | July 2023
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
2023 Conference on Learning Theory | July 2023
Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
2023 Conference on Learning Theory | July 2023
Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
Andrew Wagenmaker, Dylan Foster
2023 Conference on Learning Theory | July 2023
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
Dylan Foster, Noah Golowich, Yanjun Han
2023 Conference on Learning Theory | July 2023
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
Dylan Foster, Noah Golowich, Sham M. Kakade
ICML 2023 | June 2023
The Role of Coverage in Online Reinforcement Learning
Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
2023 International Conference on Learning Representations | May 2023
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
ICML 2023 | April 2023
On the Complexity of Adversarial Decision Making
Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
NeurIPS 2022 | November 2022
Oral presentation
Interaction-Grounded Learning with Action-Inclusive Feedback
Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
NeurIPS 2022 | November 2022
Understanding the Eluder Dimension
Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
2022 Neural Information Processing Systems | October 2022
Contextual Bandits with Large Action Spaces: Made Practical
Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
2022 International Conference on Machine Learning | July 2022
Lower Bounds for Non-Convex Stochastic Optimization
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
Mathematical Programming | May 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022 Conference on Learning Theory | May 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
2022 Conference on Learning Theory | May 2022
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
2021 Conference on Learning Theory | July 2021
-
Lower Bounds for Non-Convex Stochastic Optimization
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
Mathematical Programming | May 2022
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
2021 Conference on Learning Theory | July 2021
Publications by Type
-
The Power of Resets in Online Reinforcement Learning
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
NeurIPS 2024 | October 2024
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Dylan Foster, Adam Block, Dipendra Misra
NeurIPS 2024 | July 2024
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
Fan Chen, Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin, Yunbei Xu
NeurIPS 2024 | May 2024
Online Estimation via Offline Estimation: An Information-Theoretic Framework
Dylan Foster, Yanjun Han, Jian Qian, Alexander Rakhlin
NeurIPS 2024 | April 2024
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
Harnessing Density Ratios for Online Reinforcement Learning
P. Amortila, Dylan Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
ICLR 2024 | January 2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
Dylan Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
2023 Conference on Learning Theory | July 2023
Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
Aleksandrs Slivkins (slivkins), Karthik Abinav Sankararaman, Dylan Foster
2023 Conference on Learning Theory | July 2023
Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory
Andrew Wagenmaker, Dylan Foster
2023 Conference on Learning Theory | July 2023
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
Dylan Foster, Noah Golowich, Yanjun Han
2023 Conference on Learning Theory | July 2023
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
Dylan Foster, Noah Golowich, Sham M. Kakade
ICML 2023 | June 2023
The Role of Coverage in Online Reinforcement Learning
Tengyang Xie, Dylan Foster, Yu Bai, Nan Jiang, Sham Kakade
2023 International Conference on Learning Representations | May 2023
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
Zakaria Mhammedi, Dylan Foster, Alexander Rakhlin
ICML 2023 | April 2023
On the Complexity of Adversarial Decision Making
Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
NeurIPS 2022 | November 2022
Oral presentation
Interaction-Grounded Learning with Action-Inclusive Feedback
Tengyang Xie, Akanksha Saran, Dylan J Foster, Lekan P Molu, Ida Momennejad, Nan Jiang, Paul Mineiro, John Langford
NeurIPS 2022 | November 2022
Understanding the Eluder Dimension
Gene Li, Pritish Kamath, Dylan Foster, Nathan Srebro
2022 Neural Information Processing Systems | October 2022
Contextual Bandits with Large Action Spaces: Made Practical
Yinglun Zhu, Dylan Foster, John Langford, Paul Mineiro
2022 International Conference on Machine Learning | July 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
2022 Conference on Learning Theory | May 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
2022 Conference on Learning Theory | May 2022
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
Dylan Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu
2021 Conference on Learning Theory | July 2021
-
Minimax Rates for Conditional Density Estimation via Empirical Entropy
Blair Bilodeau, Dylan Foster, Daniel M. Roy
Annals of Statistics | July 2023
Lower Bounds for Non-Convex Stochastic Optimization
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan Foster, Nathan Srebro, Blake E. Woodworth
Mathematical Programming | May 2022