Table 9 Results comparison of scheduling score and RPD in different methods on Orb data cases.

From: A novel method-based reinforcement learning with deep temporal difference network for flexible double shop scheduling problem

Prob. (%)

FIFO

SPT

LPT

SRPT

LRPT

MOR

EDD

QL

DDPG

DTDN

Score

Score

Score

Score

Score

Score

Score

Score

RPD

Score

RPD

Score

RPD

Case06

7.74e2

7.17e2

7.51e2

7.03e2

7.41e2

7.56e2

6.66e2

9.18e2

1.98e−2

8.75e2

0.1435

8.75e2

1.44e−1

Case07

8.81e2

7.56e2

6.87e2

6.54e2

6.86e2

7.64e2

6.83e2

9.54e2

4.48e−2

8.86e2

0.1284

8.86e2

1.28e−1

Case08

7.15e2

8.52e2

7.03e2

6.96e2

7.01e2

7.15e2

6.75e2

9.18e2

8.96e−2

8.74e2

0.1443

8.51e2

1.75e−1

Case09

7.59e2

8.13e2

7.10e2

6.82e2

7.32e2

7.02e2

7.03e2

9.41e2

6.27e−2

8.88e2

0.1264

8.55e2

1.70e−1

Case10

7.68e2

7.70e2

8.07e2

7.83e2

6.92e2

7.31e2

7.13e2

9.09e2

1.00e−1

8.49e2

0.1701

8.48e2

1.79e−1

Case11

7.59e2

8.49e2

6.85e2

6.67e2

7.02e2

6.98e2

6.82e2

9.49e2

5.35e−2

9.13e2

0.0951

8.49e2

1.78e−1

Case12

8.36e2

7.88e2

8.45e2

8.02e2

6.99e2

7.42e2

7.05e2

9.36e2

6.80e−2

8.48e2

0.1788

8.63e2

1.59e−1

Case13

7.34e2

8.12e2

7.65e2

7.72e2

8.20e2

7.92e2

7.36e2

9.40e2

6.34e−2

8.80e2

0.1369

8.14e2

2.29e−1

Case14

7.86e2

7.40e2

7.26e2

6.41e2

6.53e2

6.87e2

6.93e2

9.38e2

6.63e−2

8.63e2

0.1585

8.49e2

1.78e−1

Case15

7.79e2

7.89e2

7.42e2

7.11e2

7.13e2

7.32e2

6.95e2

9.34e2

7.11e−2

9.75e2

0.1424

8.54e2

1.71e−1