Thomas Coste

~Thomas_Coste1

3

论文总数

1.5

年均投稿

7.1

平均评分

接收情况3/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20252 篇

Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control

NeurIPS 2025Poster

Lightweight Neural App Control

ICLR 2025Spotlight

20241 篇

Reward Model Ensembles Help Mitigate Overoptimization

ICLR 2024Poster

合作者 (8)

Georgios Papoudakis2 篇

Jianye HAO2 篇

Filippos Christianos1 篇

David Krueger1 篇

Robert Kirk1 篇

Usman Anwar1 篇