Table 4 Cross-validation of batch size and update frequency.

From: Design of a dynamic trust management and defense decision system for shared vehicle data based on blockchain and deep reinforcement learning

Batch size

Update frequency

Average reward

Training time (hours)

16

25

79.3

7.2

50

80.1

7.8

100

77.6

6.9

32

25

81.2

8.1

50

82.8

8.5

100

80.9

8.3

64

25

75.4

9.2

50

76.8

9.7

100

74.1

9.0

Back to article page