Yunhao Tang

Research Scientist, DeepMind

Joined

September 2018

Names

Yunhao Tang (Preferred)

Emails

****@columbia.edu (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Research Scientist

DeepMind (deepmind.com)

2021 – Present

PhD student

Columbia University (columbia.edu)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Reinforcement Learning

2017 – Present

Publications

Discrete action on-policy learning with action-value critic
Yuguang Yue, Yunhao Tang, Mingzhang Yin, Mingyuan Zhou
- International Conference on Artificial Intelligence and Statistics
- Readers: Everyone
RL-finetuning LLMs from on- and off-policy data with a single algorithm
Yunhao Tang, Taco Cohen, David W. Zhang, Gabriel Synnaeve, Rémi Munos
- AISTATS 2026 Poster
- Readers: Everyone
Off-policy Distributional Q($\lambda$): Distributional RL without Importance Sampling
Yunhao Tang, Mark Rowland, Rémi Munos, Bernardo Avila Pires, Will Dabney
- AISTATS 2026 Poster
- Readers: Everyone
Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
Charles Arnal, Gaëtan Narozniak, Vivien Cabannes, Yunhao Tang, Julia Kempe, Remi Munos
- NeurIPS 2025 poster
- Readers: Everyone
Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
Yunhao Tang, Sid Wang, Lovish Madaan, Remi Munos
- NeurIPS 2025 poster
- Readers: Everyone
Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
Tyler Kastner, Mark Rowland, Yunhao Tang, Murat A Erdogdu, Amir-massoud Farahmand
- ICML 2025 poster
- Readers: Everyone
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Remi Munos
- ICML 2025 poster
- Readers: Everyone
A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires, Yunhao Tang, Clare Lyle, Mark Rowland, Nicolas Heess, Diana L Borsa, Arthur Guez, Will Dabney
- AISTATS 2025 Poster
- Readers: Everyone
A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning
Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires, Yunhao Tang, Clare Lyle, Mark Rowland, Nicolas Heess, Diana L Borsa, Arthur Guez, Will Dabney
- NeurIPS 2024 Workshop SSL
- Readers: Everyone
A Distributional Analogue to the Successor Representation
Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Yunhao Tang, Andre Barreto, Will Dabney, Marc G Bellemare, Mark Rowland
- EWRL17
- Readers: Everyone

View all 34 publications

Co-Authors

View all 106 co-authors