Jianye Hao's Homepage
     
    Jianye Hao

    Associate Professor

    Tianjin University
    Tianjin, China, 300350

    Deep Reinforcement Learning Lab

    Email
    jianye.hao@tju.edu.cn

       

    Jianye Hao is an Associate Professor at College of Intelligence and Computing ,Tianjin University.

    Jianye's research focuses on deep reinforcement learning and multiagent systems and apply those techniques and methodologies to address large-scale and dynamic decision-making problems including game AI (deployed in a number of commercial game products in Netease), ads display optimization in e-commerce (deployed in Alibaba's Taobao Platform), Auto-Driving, Wireless network and Data center optimization and so on.

    Education:
    • 2013.9-2015.4: MIT-SUTD Joint Postdoc Researcher
    • 2009.7-2013.7: The Chinese University of Hong Kong , Computer Science and Engineering, PhD
    • 2004.9-2008.7: Harbin Institute of Technology , Computer Science and Technology, Bachelor of Engineering
    Academic Experience:
    • Visiting Scholar at School of Computer Science and Software Engineering, University of Wollongong, Sep 2014 - Oct 2014, Host: Prof. Minjie Zhang
    • Visiting Scholar at School of Computing, National University of Singapore, July, 2011 - December, 2011, Host:Prof. Jin Song Dong
    Research:

    Current research focuses on :

    • Multiagent Systems (multiagent learning, game theory, automated negotiation)
    • Artificial Intelligence (Deep Reinforcement Learning, Machine Learning)

      • See more details at: Research page

    Publications:
    • PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration, ICML, 2022
    • Learning Pseudometric-based Action Representations for Offline Reinforcement Learning, ICML, 2022
    • HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation, ICLR, 2022
    • What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator, AAAI, 2022
    • A Reinforcement Learning Based Bi-level Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems, NIPS, 2021
    • An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning, NIPS, 2021
    • Principled Exploration via Optimistic Bootstrapping and Backward Induction, ICML, 2021
    • A Multi-Graph Attributed Reinforcement Learning based Optimization Algorithm for Large-scale Hybrid Flow Shop Scheduling Problem, KDD, 2021
    • Automatic Web Testing using Curiosity-Driven Reinforcement Learning, ICSE, 2021
    • Addressing Action Oscillations through Learning Policy Inertia, AAAI, 2021
    • Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction, AAAI, 2021
    • Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning, AAAI, 2021
    • Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping, NeurIPS, 2020
    • Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising, ICML, 2020
    • Q-value Path Decomposition for Deep Multiagent Reinforcement Learning, ICML, 2020
    • Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets, IJCAI, 2020
    • Learning to Accelerate Heuristic Searching for Large-Scale MaximumWeighted b-Matching Problems in Online Advertising, IJCAI, 2020
    • Generating Behavior-Diverse Game AIs with Evolutionary Multi-Objectives Deep Reinforcement Learning, IJCAI, 2020

      • See more details at: Publication page

    Groups:

    PhD students:

    • Tianpei Yang, PhD, 3rd year - Policy Transfer in multiagent systems
    • Weixun Wang, PhD, 2nd year - Large-scale multiagent learning
    • Hongyao Tang, PhD, 2nd year - Hierachical model-based Reinforcement learnings
    • Xiaotian Hao, PhD, 1st year - Learning to optimize using reinforcement learning
    • Yi Ma, PhD, 1st year - Learning to solve combinatorial optimization problems using reinforcement learning

      • See more details at: Team page

    Selected Rewards:
    • Best System Paper Award in CoRL 2020:" SMARTS: An Open-Source Scalable Multi-Agent RL Training School for Autonomous Driving", 2020
    • ACM SIGSOFT Distinguished Paper Award in ASE 2019:" Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning", 2019
    • Best Paper Award in DAI 2019:" Achieving Cooperation Through Deep Multiagent Reinforcement Learning in Sequential Prisoner's Dilemmas", 2019
    • CCF Young Scholar Award, 2017-2020.
    • Tianjin Young Talent 1000 Plan, 2015-2018.
    • Second Place in The Fifth International Automated Negotiating Agent Competition (ANAC2015) at AAMAS 2015, Turkey, 2015.
    • Endeavour Research Fellowship, 2014-2015.
    • Champion of The Third International Automated Negotiating Agent Competition (ANAC 2012) at AAMAS 2012 , Spain, 2012.
    • The Best Agent in Discounted Domains in The Third International Automated Negotiating Agent Competition (ANAC 2012) at AAMAS 2012.
    • Global Scholarship for Research Excellence - awarded by The Chinese University of Hong Kong, 2011.
    Professional Services:
    • Organizer
        • - PRICAI 2018 Co-PC chair (Reinforcement Learning Track)
        - DAI 2019 Publicity Chair, 2020 Sponsor Chair
        - Co-chair of CCML workshop on Reinforcement Learning, 2017
        - Co-chair of International Workshop on Multiagent Learning: Theory and Application, 2016
    • (Senior) Program Committee Member of AAAI、IJCAI、ICML、NeurIPS、AAMAS、CIKM
    Teaching Experience
    • Introduction to Artificial Intelligence, 2015-present, Tianjin University
    • Advanced Artificial Intelligence, 2015-present, Tianjin University
    • Advanced Big Data, 2015-2018, Tianjin University