Minimizing the Cost of Spatiotemporal Searches Based on Reinforcement Learning with Probabilistic States

Table 1

Detailed description of the dataset.

(a) Raw data details

Field name	Example	Remarks
Vehicle ID	1	\
Passenger or not	0/1	\
Timestamp	1501584540	Unix timestamp, in seconds
Longitude	104.042833	GCJ-02
Latitude	30.599851	GCJ-02

(b) Complete trajectory of a vehicle in a day

Vehicle	Day	Longitude	Latitude	Moment
	2014/8/4	104.039163	30.597572	7 : 00
		104.126565	30.599733	7 : 01
		...	...	...
		104.042833	30.599851	21 : 58
		104.127154	30.600009	21 : 59