Table 4 The operating points of Bell and Astrom boiler model3.

From: Novel multiagent reinforcement learning framework using twin delayed deep deterministic policy gradient for adaptive PID control in boiler turbine systems

#

u\(_{1\text {-BTS}^{0}}\)

u\(_{2\text {-BTS}^{0}}\)

u\(_{3\text {-BTS}^{0}}\)

x\(_{1\text {-BTS}^{0}}\)

x\(_{2\text {-BTS}^{0}}\)

x\(_{3\text {-BTS}^{0}}\)

y\(_{3\text {-BTS}^{0}}\)

1

0.1560

0.4830

0.1830

75.60

15.270

299.60

-0.970

2

0.2090

0.5520

0.2560

86.40

36.650

342.40

-0.650

3

0.2710

0.6210

0.340

97.20

50.520

385.20

-0.320

4

0.3400

0.6900

0.4330

108.00

66.650

428.00

0.000

5

0.4180

0.7590

0.5430

118.80

85.060

470.80

0.320

6

0.5050

0.8280

0.6630

129.60

105.800

513.60

0.640

7

0.6000

0.8970

0.7930

140.40

128.900

556.40

0.980