【论文随笔】Model-based Reinforcement Learning from Signal Temporal Logic Specifications
参考文献:P.Kapoor,A.Balakrishnan,andJ.V.Deshmukh,“Model-basedReinforcementLearningfromSignalTemporalLogicSpecifications.”arXiv,Nov.10,2020.doi:10.48550/arXiv.2011.04950.Outline用DNN来学习系统动态,用于MPC的轨迹生成优化目标为S