Alert button
Picture for Dylan J. Foster

Dylan J. Foster

Alert button

Can large language models explore in-context?

Add code
Bookmark button
Alert button
Mar 22, 2024
Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster, Cyril Zhang, Aleksandrs Slivkins

Viaarxiv icon

Scalable Online Exploration via Coverability

Add code
Bookmark button
Alert button
Mar 11, 2024
Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy

Figure 1 for Scalable Online Exploration via Coverability
Figure 2 for Scalable Online Exploration via Coverability
Figure 3 for Scalable Online Exploration via Coverability
Figure 4 for Scalable Online Exploration via Coverability
Viaarxiv icon

Harnessing Density Ratios for Online Reinforcement Learning

Add code
Bookmark button
Alert button
Jan 18, 2024
Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie

Viaarxiv icon

Foundations of Reinforcement Learning and Interactive Decision Making

Add code
Bookmark button
Alert button
Dec 27, 2023
Dylan J. Foster, Alexander Rakhlin

Viaarxiv icon

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Add code
Bookmark button
Alert button
Oct 17, 2023
Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang

Viaarxiv icon

Efficient Model-Free Exploration in Low-Rank MDPs

Add code
Bookmark button
Alert button
Jul 08, 2023
Zakaria Mhammedi, Adam Block, Dylan J. Foster, Alexander Rakhlin

Viaarxiv icon

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

Add code
Bookmark button
Alert button
May 01, 2023
Dylan J. Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin

Viaarxiv icon

Instance-Optimality in Interactive Decision Making: Toward a Non-Asymptotic Theory

Add code
Bookmark button
Alert button
Apr 24, 2023
Andrew Wagenmaker, Dylan J. Foster

Viaarxiv icon

Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL

Add code
Bookmark button
Alert button
Apr 12, 2023
Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin

Figure 1 for Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
Figure 2 for Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
Viaarxiv icon

Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games

Add code
Bookmark button
Alert button
Mar 22, 2023
Dylan J. Foster, Noah Golowich, Sham M. Kakade

Viaarxiv icon