activity
20172022
most citedBayesian Optimization with Unknown Search Space

25 citations · 34 across the 5 of their papers we have counts for

collaborators

9 papers

cs.IR2022★ 2 cited

Two-Stage Neural Contextual Bandits for Personalised News Recommendation

Mengyan Zhang, Thanh Nguyen-Tang, Fangzhao Wu +3

We consider the problem of personalised news recommendation where each user consumes news in a sequential fashion. Existing personalised news recommendation methods focus on exploi…

cs.LG2022

On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency

Thanh Nguyen-Tang

This thesis rigorously studies fundamental reinforcement learning (RL) methods in modern practical considerations, including robust RL, distributional RL, and offline RL with neura…

cs.LG2021

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

Thanh Nguyen-Tang, Sunil Gupta, A. Tuan Nguyen +1

Offline policy learning (OPL) leverages existing data collected a priori for policy optimization without any active exploration. Despite the prevalence and recent interest in this…

stat.ML2021★ 1 cited

Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support

Hung Tran-The, Sunil Gupta, Thanh Nguyen-Tang +2

We address policy learning with logged data in contextual bandits. Current offline-policy learning algorithms are mostly based on inverse propensity score (IPS) weighting requiring…

stat.ML2021

Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks

Thanh Nguyen-Tang, Sunil Gupta, Hung Tran-The +1

Offline reinforcement learning (RL) leverages previously collected data for policy optimization without any further active exploration. Despite the recent interest in this problem,…

cs.LG2020

Distributional Reinforcement Learning via Moment Matching

Thanh Tang Nguyen, Sunil Gupta, Svetha Venkatesh

We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-ar…