DDCL: A Dual Decision-making Continuous Reinforcement Learning Method Based on Sim2Real.
Wenwen XiaoXinzhi WangXiangfeng LuoShaorong XiePublished in: SEKE (2023)
Keyphrases
- decision making
- reinforcement learning
- clustering method
- dynamic programming
- experimental evaluation
- optimization algorithm
- preprocessing
- support vector machine svm
- prior knowledge
- evaluation method
- synthetic data
- high accuracy
- state space
- significant improvement
- pairwise
- decision support system
- multi agent
- objective function
- detection method
- machine learning
- data sets