首页|New Robotics Study Results from Beijing Institute of Technology Described (Desig n of Self-Organizing Systems Using Multi-Agent Reinforcement Learning and the Co mpromise Decision Support Problem Construct)
New Robotics Study Results from Beijing Institute of Technology Described (Desig n of Self-Organizing Systems Using Multi-Agent Reinforcement Learning and the Co mpromise Decision Support Problem Construct)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ro botics. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "In this paper, we address the following q uestion: How can multi-robot self-organizing systems be designed so that they sh ow the desired behavior and are able to perform tasks specified by the designers ? Multi-robot self-organizing systems, e.g., swarm robots, have great potential for adapting when performing complex tasks in a changing environment. However, s uch systems are difficult to design due to the stochasticity of system performan ce and the non-linearity between the local actions/interaction and the desired g lobal behavior." The news correspondents obtained a quote from the research from Beijing Institut e of Technology: "In order to address this, in this paper, we propose a framewor k for designing self-organizing systems using Multi-Agent Reinforcement Learning (MARL) and the compromise Decision-Support Problem (cDSP) construct. The propos ed framework consists of two stages, namely, preliminary design followed by desi gn improvement. In the preliminary design stage, MARL is used to help designers train the robots so that they show stable group behavior for performing the task . In the design improvement stage, the cDSP construct is used to explore the des ign space and identify satisfactory solutions considering several performance in dicators. Surrogate models are used to map the relationship between local parame ters and global performance indicators utilizing the data generated in the preli minary design. These surrogate models represent the goals of the cDSP."
Beijing Institute of TechnologyBeijingPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningNan o-robotReinforcement LearningRobotRobotics
NETL
NSTL
