Picture for Lillian J. Ratliff

Lillian J. Ratliff

Initializing Services in Interactive ML Systems for Diverse Users

Dec 19, 2023
Viaarxiv icon

Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits

Add code
Oct 25, 2023
Viaarxiv icon

Logarithmic Regret for Matrix Games against an Adversary with Noisy Bandit Feedback

Jun 22, 2023
Viaarxiv icon

Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula

May 04, 2023
Figure 1 for Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Figure 2 for Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Figure 3 for Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Figure 4 for Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Viaarxiv icon

Human adaptation to adaptive machines converges to game-theoretic equilibria

Add code
May 01, 2023
Figure 1 for Human adaptation to adaptive machines converges to game-theoretic equilibria
Figure 2 for Human adaptation to adaptive machines converges to game-theoretic equilibria
Figure 3 for Human adaptation to adaptive machines converges to game-theoretic equilibria
Figure 4 for Human adaptation to adaptive machines converges to game-theoretic equilibria
Viaarxiv icon

Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games

Mar 19, 2023
Viaarxiv icon

Multi-learner risk reduction under endogenous participation dynamics

Jun 06, 2022
Figure 1 for Multi-learner risk reduction under endogenous participation dynamics
Figure 2 for Multi-learner risk reduction under endogenous participation dynamics
Viaarxiv icon

General sum stochastic games with networked information flows

May 05, 2022
Figure 1 for General sum stochastic games with networked information flows
Figure 2 for General sum stochastic games with networked information flows
Figure 3 for General sum stochastic games with networked information flows
Figure 4 for General sum stochastic games with networked information flows
Viaarxiv icon

Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments

Add code
Apr 08, 2022
Figure 1 for Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
Figure 2 for Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
Figure 3 for Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
Figure 4 for Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
Viaarxiv icon

Multiplayer Performative Prediction: Learning in Decision-Dependent Games

Add code
Jan 10, 2022
Figure 1 for Multiplayer Performative Prediction: Learning in Decision-Dependent Games
Figure 2 for Multiplayer Performative Prediction: Learning in Decision-Dependent Games
Figure 3 for Multiplayer Performative Prediction: Learning in Decision-Dependent Games
Figure 4 for Multiplayer Performative Prediction: Learning in Decision-Dependent Games
Viaarxiv icon