Skip to main content

Table 3 Benchmark results of the CRLV-biased-G: last epoch

From: Conditional reduction of the loss value versus reinforcement learning for biassing a de-novo drug design generator

Objective

Validity

Novelty

Uniqueness

intDiv

Desirability

1

70.53

78.16

70.45

0.77

57.00 = 2214

2

54.29

90.38

93.49

0.80

25.54 = 1172

3

61.55

87.08

67.51

0.81

12.01 = 434

4

66.37

86.98

73.94

0.82

1.71 = 73