22 citations · 31 across the 8 of their papers we have counts for
8 papers
DIFFER: Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
Xunhan Hu, Jian Zhao, Wengang Zhou +2
Cooperative multi-agent reinforcement learning (MARL) is a challenging task, as agents must learn complex and diverse individual strategies from a shared team reward. However, exis…
Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation
Chenxu Wang, Fuli Feng, Yang Zhang +3
Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A stan…
LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning
Mingyu Yang, Jian Zhao, Xunhan Hu +3
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 age…
DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning
Youpeng Zhao, Jian Zhao, Xunhan Hu +2
Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular c…
Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents
Jian Zhao, Youpeng Zhao, Weixun Wang +5
Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap…
CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning
Jian Zhao, Xunhan Hu, Mingyu Yang +3
Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has…
Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization
Jian Zhao, Yue Zhang, Xunhan Hu +5
In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards. In the absence of individual reward signals, credit assignm…
MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning
Jian Zhao, Mingyu Yang, Youpeng Zhao +4
In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interact…