A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems

Table 2

Information of training datasets for the HMM.

Name of the dataset	Number of traces	Number of explored states	Percentage of traces in the test dataset covered by the training dataset
HMM-50	50,000	279,477	0
HMM-100a	100,000	384,623	79
HMM-100b	100,000	384,621	0
HMM-200a	200,000	492,642	79
HMM-200b	200,000	492,645	0