4 citations · 4 across the 3 of their papers we have counts for
5 papers · 1 filter
Uncertainty-Normalized Margins for Direct Preference Optimization
Sadegh Khorasani, Petrus Mikkola, Matthias Grossglauser
Direct preference optimization (DPO) models binary preferences through a Bradley-Terry model with a common noise scale, without explicitly accounting for preference strength or pro…
Differentiable Structure Learning for Cyclic Linear Gaussian Models with Latent Confounders
Sadegh Khorasani, Ali Najar, Saber Salehkaleybar +1
We study causal structure learning from observational data in linear Gaussian structural causal models in the presence of directed cycles and an unknown number of exogenous latent…
Fusing Rewards and Preferences in Reinforcement Learning
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +1
We present Dual-Feedback Actor (DFA), a reinforcement learning algorithm that fuses both individual rewards and pairwise preferences (if available) into a single update rule. DFA u…
Hierarchical Reinforcement Learning with Targeted Causal Interventions
Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash +1
Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgo…
Momentum-Based Policy Gradient with Second-Order Information
Saber Salehkaleybar, Sadegh Khorasani, Negar Kiyavash +2
Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleratio…