Picture for Lillian Ratliff

Lillian Ratliff

Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning

Jun 11, 2024
Viaarxiv icon

Coupled Gradient Flows for Strategic Non-Local Distribution Shift

Jul 07, 2023
Figure 1 for Coupled Gradient Flows for Strategic Non-Local Distribution Shift
Figure 2 for Coupled Gradient Flows for Strategic Non-Local Distribution Shift
Figure 3 for Coupled Gradient Flows for Strategic Non-Local Distribution Shift
Figure 4 for Coupled Gradient Flows for Strategic Non-Local Distribution Shift
Viaarxiv icon

Convergent First-Order Methods for Bi-level Optimization and Stackelberg Games

Feb 02, 2023
Viaarxiv icon

Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games

Jul 18, 2022
Figure 1 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
Figure 2 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
Figure 3 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
Figure 4 for Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
Viaarxiv icon

Instance-optimal PAC Algorithms for Contextual Bandits

Jul 05, 2022
Figure 1 for Instance-optimal PAC Algorithms for Contextual Bandits
Viaarxiv icon

Online Learning in Periodic Zero-Sum Games

Nov 05, 2021
Figure 1 for Online Learning in Periodic Zero-Sum Games
Figure 2 for Online Learning in Periodic Zero-Sum Games
Figure 3 for Online Learning in Periodic Zero-Sum Games
Figure 4 for Online Learning in Periodic Zero-Sum Games
Viaarxiv icon

Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

Add code
Dec 15, 2020
Figure 1 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Figure 2 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Figure 3 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Figure 4 for Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Viaarxiv icon

Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation

Add code
Sep 30, 2020
Figure 1 for Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
Figure 2 for Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
Figure 3 for Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
Figure 4 for Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation
Viaarxiv icon

A $\texttt{SUPER}^{\ast}$ Algorithm to Optimize Paper Bidding in Peer Review

Add code
Jun 27, 2020
Figure 1 for A $\texttt{SUPER}^{\ast}$ Algorithm to Optimize Paper Bidding in Peer Review
Figure 2 for A $\texttt{SUPER}^{\ast}$ Algorithm to Optimize Paper Bidding in Peer Review
Figure 3 for A $\texttt{SUPER}^{\ast}$ Algorithm to Optimize Paper Bidding in Peer Review
Figure 4 for A $\texttt{SUPER}^{\ast}$ Algorithm to Optimize Paper Bidding in Peer Review
Viaarxiv icon

Sequential Experimental Design for Transductive Linear Bandits

Add code
Jun 20, 2019
Figure 1 for Sequential Experimental Design for Transductive Linear Bandits
Viaarxiv icon