Picture for Asuman Ozdaglar

Asuman Ozdaglar

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback

May 20, 2024
Viaarxiv icon

Uniformly Stable Algorithms for Adversarial Training and Beyond

Add code
May 03, 2024
Viaarxiv icon

Principled RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation

Apr 30, 2024
Figure 1 for Principled RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation
Viaarxiv icon

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

Add code
Mar 25, 2024
Figure 1 for Do LLM Agents Have Regret? A Case Study in Online Learning and Games
Figure 2 for Do LLM Agents Have Regret? A Case Study in Online Learning and Games
Figure 3 for Do LLM Agents Have Regret? A Case Study in Online Learning and Games
Figure 4 for Do LLM Agents Have Regret? A Case Study in Online Learning and Games
Viaarxiv icon

Matching of Users and Creators in Two-Sided Markets with Departures

Jan 17, 2024
Viaarxiv icon

Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games

Dec 08, 2023
Viaarxiv icon

EM for Mixture of Linear Regression with Clustered Data

Aug 22, 2023
Viaarxiv icon

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

Jul 13, 2023
Figure 1 for Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
Figure 2 for Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
Figure 3 for Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
Figure 4 for Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
Viaarxiv icon

A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games

Mar 03, 2023
Viaarxiv icon

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation

Dec 28, 2022
Viaarxiv icon