Milad Aghajohari

~Milad_Aghajohari1

6

论文总数

3.0

年均投稿

5.5

平均评分

接收情况3/6

会议分布

ICLR

5

ICML

1

发表论文 (6 篇)

20253 篇

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

ICLR 2025Rejected

VinePPO: Refining Credit Assignment in RL Training of LLMs

ICML 2025Poster

Advantage Alignment Algorithms

20243 篇

Best Response Shaping

ICLR 2024Rejected

LOQA: Learning with Opponent Q-Learning Awareness

ICLR 2024Poster

Meta-Value Learning: a General Framework for Learning with Learning Awareness

ICLR 2024Rejected

合作者 (12)

Aaron Courville6 篇

Tim Cooijmans4 篇

Juan Agustin Duque3 篇

Alessandro Sordoni2 篇

Amirhossein Kazemnejad2 篇

Eva Portelance2 篇

Nicolas Le Roux2 篇

Siva Reddy2 篇