3 papers
cs.LG2026
Information-Directed Sampling for Causal Bandits
Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi
Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions. In many applic…
stat.ML2025
Characterization and Learning of Causal Graphs from Hard Interventions
Zihan Zhou, Muhammad Qasim Elahi, Murat Kocaoglu
A fundamental challenge in the empirical sciences involves uncovering causal structure through observation and experimentation. Causal discovery entails linking the conditional ind…
cs.LG2025
Reinforcement Learning from Multi-level and Episodic Human Feedback
Muhammad Qasim Elahi, Somtochukwu Oguchienti, Maheed H. Ahmed +1
Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various le…