Pan Ying

Learn More
Cooperation among agents is important for multi-agent system. In this paper, an improved cooperative reinforcement learning algorithm is proposed, which based on joint rewards to insure agents to learn cooperative behavior. Furthermore, a symmetry idea is included in the algorithm to reduce the states size of reinforcement learning. The experiment results(More)
To achieve automatic logistics supply for the front combat troops in a combat simulation, a multi-agent cooperative simulation model is constructed, and a multi-agent cooperative reinforcement learning algorithm constrained by a common rule is proposed. The algorithm take the multi-agent cooperative learning process as discrete stage games, force all the(More)
  • Pan Ying
  • 2011
In this paper, the H∞control method as the static acceleration feedback was put forward concerned with structural uncertainty and actuator saturation. The sufficiency and necessary condition that the controller existed was proved. By simulation, it was shown that the structure could hold the favorable stability by H∞ robust control technique.
Establish and maintain software artifact traceability is widely recognized as one of the major challenges in software engineering research. Because of the lack of automatic or semi-automatic methodologies and technologies, traceability information is often out of date or completely missing as the software changes. We present a framework for software(More)
  • 1