Ldsa: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning

M Yang, J Zhao, X Hu, W Zhou… - Advances in neural …, 2022 - proceedings.neurips.cc
Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in
recent years. For training efficiency and scalability, most of the MARL algorithms make all …

Q-sat: Value factorization with self-attention for deep multi-agent reinforcement learning

X Hu, J Zhao, Y Zhao, W Zhou… - 2023 International Joint …, 2023 - ieeexplore.ieee.org
In many real-world tasks, a team of agents learn to cooperate with each other under the
setting of partial observability and communication constraints, where value factorization has …

CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning

J Zhao, X Hu, M Yang, W Zhou… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Due to the partial observability and communication constraints in many multiagent reinforcement
learning (MARL) tasks, centralized training with decentralized execution (CTDE) has …

Douzero+: Improving doudizhu ai by opponent modeling and coach-guided learning

Y Zhao, J Zhao, X Hu, W Zhou… - 2022 IEEE conference on …, 2022 - ieeexplore.ieee.org
Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL)
in various perfect and imperfect information games. Among these games, DouDizhu, a …

Rethinking missing data: Aleatoric uncertainty-aware recommendation

…, F Feng, Y Zhang, Q Wang, X Hu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Historical interactions are the default choice for recommender model training, which typically
exhibit high sparsity, ie, most user-item pairs are unobserved missing data. A standard …

Full douzero+: Improving doudizhu ai by opponent modeling, coach-guided training and bidding learning

Y Zhao, J Zhao, X Hu, W Zhou… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the development of deep reinforcement learning, much progress in various perfect and
imperfect information games has been achieved. Among these games, DouDizhu, a popular …

Coach-assisted multi-agent reinforcement learning framework for unexpected crashed agents

J Zhao, Y Zhao, W Wang, M Yang, X Hu… - Frontiers of Information …, 2022 - Springer
Multi-agent reinforcement learning is difficult to apply in practice, partially because of the
gap between simulated and real-world scenarios. One reason for the gap is that simulated …

Flexible Photodetector Arrays Based on Patterned CH3NH3PbI3−xClx Perovskite Film for Real‐Time Photosensing and Imaging

…, X Han, Z Yang, G Gao, Y Zhang, J Hu… - Advanced …, 2019 - Wiley Online Library
The quest for novel deformable image sensors with outstanding optoelectronic properties
and large‐scale integration becomes a great impetus to exploit more advanced flexible …

Piezo‐Phototronic Effect Modulated Deep UV Photodetector Based on ZnO‐Ga2O3 Heterojuction Microwire

M Chen, B Zhao, G Hu, X Fang, H Wang… - Advanced Functional …, 2018 - Wiley Online Library
A strain modulated solar‐blinded photodetector (PD) based on ZnO‐Ga 2 O 3 core–shell
heterojuction microwire is developed. This PD is highly sensitive to deep UV light centered at …

Cytokine storm in domestic pigs induced by infection of virulent African swine fever virus

…, T Chen, Y Wang, F Zhang, S Zhang, R Hu - Frontiers in veterinary …, 2021 - frontiersin.org
African swine fever, caused by African swine fever virus (ASFV), is a highly contagious
hemorrhagic disease of domestic pigs. The current continent-wide pandemic has persisted for …