In this paper, the reinforcement learning method for cooperative multi-agent systems(MAS) with incremental number of agents is studied. The existing multi-agent reinforcement learning approaches deal with the MAS with...In this paper, the reinforcement learning method for cooperative multi-agent systems(MAS) with incremental number of agents is studied. The existing multi-agent reinforcement learning approaches deal with the MAS with a specific number of agents, and can learn well-performed policies. However, if there is an increasing number of agents, the previously learned in may not perform well in the current scenario. The new agents need to learn from scratch to find optimal policies with others,which may slow down the learning speed of the whole team. To solve that problem, in this paper, we propose a new algorithm to take full advantage of the historical knowledge which was learned before, and transfer it from the previous agents to the new agents. Since the previous agents have been trained well in the source environment, they are treated as teacher agents in the target environment. Correspondingly, the new agents are called student agents. To enable the student agents to learn from the teacher agents, we first modify the input nodes of the networks for teacher agents to adapt to the current environment. Then, the teacher agents take the observations of the student agents as input, and output the advised actions and values as supervising information. Finally, the student agents combine the reward from the environment and the supervising information from the teacher agents, and learn the optimal policies with modified loss functions. By taking full advantage of the knowledge of teacher agents, the search space for the student agents will be reduced significantly, which can accelerate the learning speed of the holistic system. The proposed algorithm is verified in some multi-agent simulation environments, and its efficiency has been demonstrated by the experiment results.展开更多
Three-body interaction plays an important role in many-body physics,and quantum computer is efficient in simulating many-body interactions. We have experimentally demonstrated the general three-body interactions in a ...Three-body interaction plays an important role in many-body physics,and quantum computer is efficient in simulating many-body interactions. We have experimentally demonstrated the general three-body interactions in a three-qubit nuclear magnetic resonance ensemble quantum computer. Using a nuclear magnetic resonance computer we implemented general forms of three-body interactions including σ 1x σ z2 σ x3 and σ 1x σ z2 σ y3 . The results show good agreement between theory and experiment. We have also given a concise and practical formula for a general n-body interaction in terms of one-and two-body interactions.展开更多
The four-body interaction plays an important role in many-body systems, and it can exhibit interesting phase transition behaviors. In this letter, we report the experimental demonstration of a four-body interaction in...The four-body interaction plays an important role in many-body systems, and it can exhibit interesting phase transition behaviors. In this letter, we report the experimental demonstration of a four-body interaction in a four-qubit nuclear magnetic resonance quantum information processor. The strongly modulating pulse is used to implement spin selective excitation. The results show a good agreement between theory and experiment.展开更多
基金supported by the National Key R&D Program of China (2018AAA0101400)the National Natural Science Foundation of China (62173251+3 种基金61921004U1713209)the Natural Science Foundation of Jiangsu Province of China (BK20202006)the Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control。
文摘In this paper, the reinforcement learning method for cooperative multi-agent systems(MAS) with incremental number of agents is studied. The existing multi-agent reinforcement learning approaches deal with the MAS with a specific number of agents, and can learn well-performed policies. However, if there is an increasing number of agents, the previously learned in may not perform well in the current scenario. The new agents need to learn from scratch to find optimal policies with others,which may slow down the learning speed of the whole team. To solve that problem, in this paper, we propose a new algorithm to take full advantage of the historical knowledge which was learned before, and transfer it from the previous agents to the new agents. Since the previous agents have been trained well in the source environment, they are treated as teacher agents in the target environment. Correspondingly, the new agents are called student agents. To enable the student agents to learn from the teacher agents, we first modify the input nodes of the networks for teacher agents to adapt to the current environment. Then, the teacher agents take the observations of the student agents as input, and output the advised actions and values as supervising information. Finally, the student agents combine the reward from the environment and the supervising information from the teacher agents, and learn the optimal policies with modified loss functions. By taking full advantage of the knowledge of teacher agents, the search space for the student agents will be reduced significantly, which can accelerate the learning speed of the holistic system. The proposed algorithm is verified in some multi-agent simulation environments, and its efficiency has been demonstrated by the experiment results.
基金the National Natural Science Foundation of China (Grant Nos. 10374010 and 10325521) the National Basic Research Program of China (Grant No. 2006CB921106)
文摘Three-body interaction plays an important role in many-body physics,and quantum computer is efficient in simulating many-body interactions. We have experimentally demonstrated the general three-body interactions in a three-qubit nuclear magnetic resonance ensemble quantum computer. Using a nuclear magnetic resonance computer we implemented general forms of three-body interactions including σ 1x σ z2 σ x3 and σ 1x σ z2 σ y3 . The results show good agreement between theory and experiment. We have also given a concise and practical formula for a general n-body interaction in terms of one-and two-body interactions.
基金Supported by the National Natural Science Foundation of China (Grant Nos. 10775076, 10874098)National Basic Research Program of China (Grant Nos. 2006CB921106, 2009CB929402)Specialized Research Fund for the Doctoral Program of Education Ministry of China (Grant No. 20060003048)
文摘The four-body interaction plays an important role in many-body systems, and it can exhibit interesting phase transition behaviors. In this letter, we report the experimental demonstration of a four-body interaction in a four-qubit nuclear magnetic resonance quantum information processor. The strongly modulating pulse is used to implement spin selective excitation. The results show a good agreement between theory and experiment.