Haobo Fu (傅浩波)

Haobo Fu (傅浩波)

Tech Lead, Principal Researcher

Tencent AI

Haobo Fu is a principal researcher at Tencent AI Platform Department, Shenzhen, China. His main interests are new innovations in Artificial Intelligence (AI) for the game industry. These include innovative game AI applications and related research topics, such as machine learning, reinforcement learning, game theory, etc. He got his PhD in computer science from University of Birmingham in 2014, supervised by Prof. Xin Yao and Prof. Bernhard Sendhoff. His PhD program was fully funded by Honda Research Institute Europe. He was offered the Australian Government 2015 Endeavour Research Fellowship.

News

  • I have accepted the invitation to be a Area Chair for NeurIPS 2024.
  • Three papers submitted to ICML 2024
  • Three papers got accpted to ICLR 2024, with two spotlights.
  • One paper got accpted to AAAI 2024
  • We proposed a robust and opponent-aware league training method that achieved superhuman performance on StarCraft II using much less computation than AlphaStar. Accepted to NeurIPS 2023 as a spotlight.
  • Three papers got accpted to NeurIPS 2023
  • One paper got accepted to CoRL 2023
  • On 30th May 2023, our Mahjong AI LuckyJ reached 10 dan at Tenhou.net. It is by far the only Mahjong AI that reached 10 dan from scratch using under 1500 matches. Also, its stable rank (10.68 dan) surpasses all human and AIs who played more than 1000 games in the expert room at Tenhou.net.
  • One paper got accepted to ICML 2023
  • One paper got accepted to IJCAI 2023
  • Two papers got accepted to ICLR 2023
  • One paper got accepted to AAMAS 2023
  • I was in the program committee of the IJCAI 2022 Mahjong AI Competition
  • One paper got accepted to CoG 2022
  • One paper got accepted to ICML 2022
  • One paper got accepted to AAAI 2022
  • One paper got accepted to ICLR 2022
  • One paper got accepted to IJCAI 2021
  • I lead a team that won the champion of the IJCAI 2020 Mahjong AI Competition
  • I was in the Governing Board of Linux Foundation AI&Data during 2020-2021
  • ...

Experience

 
 
 
 
 
Tech Lead, Principal Researcher
Tencent AI Platform Department, Tencent
April 2016 – Present Shenzhen, China
 
 
 
 
 
Senior Researcher
Big Data Lab, Baidu
October 2014 – March 2016 Beijing, China
 
 
 
 
 
Research Fellow
School of Computer Science, University of Birmingham
June 2014 – September 2014 Birmingham, United Kingdom

Featured Publications

Equal contributors are marked.

  • [ICLR-2024] Towards Offline Opponent Modeling with In-context Learning
    Y Jing, K Li, B Liu, Y Zang, H Fu, Q Fu, J Xing, J Cheng
  • [ICLR-2024] Dynamic Discounted Counterfactual Regret Minimization
    H Xu, K Li, H Fu, Q Fu, J Xing, J Cheng
  • [ICLR-2024] Maximum Entropy Heterogeneous-Agent Reinforcement Learning
    J Liu, Y Zhong, S Hu, H Fu, Q Fu, X Chang, Y Yang
  • [NeurIPS-2023] Policy space diversity for non-transitive games
    J Yao, W Liu, H Fu, Y Yang, S McAleer, Q Fu, W Yang
  • [NeurIPS-2023] Automatic grouping for efficient cooperative multi-agent reinforcement learning
    Y Zang, J He, K Li, H Fu, Q Fu, J Xing, J Cheng
  • [NeurIPS-2023] A robust and opponent-aware league training method for starcraft ii
    R Huang, X Wu, H Yu, Z Fan, H Fu, Q Fu, W Yang
  • [ICML-2023] Opponent-Limited Online Search for Imperfect Information Games
    W Liu, H Fu, Q Fu, W Yang
  • [ICLR-2023] Curriculum-based Co-design of Morphology and Control of Voxel-based Soft Robots
    Y Wang, S Wu, H Fu, Q Fu, T Zhang, Y Chang, X Wang
  • [ICLR-2023] Quality-Similar Diversity via Population Based Reinforcement Learning
    S Wu, J Yao, H Fu, Y Tian, C Qian, Y Yang, Q Fu, Y Wei
  • [ICML-2022] Greedy when Sure and Conservative when Uncertain about the Opponents
    H Fu, Y Tian, H Yu, W Liu, S Wu, J Xiong, Y Wen, K Li, J Xing, Q Fu, W Yang
  • [AAAI-2022] AutoCFR: Learning to Design Counterfactual Regret Minimization Algorithms
    H Xu, K Li, H Fu, Q Fu, J Xing
  • [ICLR-2022] Actor-critic policy optimization in a large-scale imperfect-information game
    H Fu, W Liu, S Wu, Y Wang, T Yang, K Li, J Xing, B Li, B Ma, Q Fu, W Yang
  • [IJCAI-2021] Combining Tree Search and Action Prediction for State-of-the-Art Performance in DouDiZhu
    Y Zhang, D Yan, B Shi, H Fu, Q Fu, H Su, J Zhu, N Chen
  • [TEVC-2014] Robust optimization over time: Problem difficulties and benchmark problems
    H Fu, B Sendhoff, K Tang, X Yao

Academic Collaborators

Contact

Any form of discussion and collaboration are warmly welcomed!