折扣系数γ | 最优维修策略 | 最优维修行为的Q值$ \times 10\;000 $![]() ![]() | 0.15 | [$ {a}_{1},{a}_{1},{a}_{1},{a}_{1},{a}_{2},{a}_{3},{a}_{4} $] | [−0.36, −0.41, −0.55 ,-0.63, −1.10, −1.60, −2.77] | 0.25 | [$ {a}_{1},{a}_{1},{a}_{1},{a}_{1},{a}_{2},{a}_{3},{a}_{4} $] | [−0.45, −0.53, −0.71, −0.81, −1.26, −1.77, −2.83] | 0.35 | [$ {a}_{1},{a}_{1},{a}_{1},{a}_{1},{a}_{2},{a}_{3},{a}_{4} $] | [−0.60, −0.69, −0.90, −1.05, −1.48, −1.99, −2.94] | 0.45 | [$ {a}_{1},{a}_{1},{a}_{1},{a}_{1},{a}_{2},{a}_{3},{a}_{4} $] | [−0.82, −0.93, −1.18, −1.34, −1.79, −2.29, −3.12] | 0.55 | [$ {a}_{1},{a}_{2},{a}_{2},{a}_{1},{a}_{3},{a}_{3},{a}_{4} $] | [−1.16, −1.30, −1.61, −1.79, −2.22, −2.73, −3.41] | 0.65 | [$ {a}_{1},{a}_{2},{a}_{2},{a}_{1},{a}_{4},{a}_{4},{a}_{4} $] | [−1.67, −1.75, −2.12, −2.42, −2.79, −3.25, −3.87] | 0.75 | [$ {a}_{1},{a}_{2},{a}_{3},{a}_{0},{a}_{4},{a}_{4},{a}_{4} $] | [−2.47, −2.53, −2.91, −3.29, −3.67, −4.03, −4.64] | 0.85 | [$ {a}_{1},{a}_{2},{a}_{3},{a}_{4},{a}_{4},{a}_{4},{a}_{4} $] | [−4.32, −4.32, −4.72, −5.17, −5.38, −5.83, −6.44] | 0.95 | [$ {a}_{1},{a}_{2},{a}_{3},{a}_{4},{a}_{4},{a}_{4},{a}_{4} $] | [−13.41, −13.37, −13.75, −14.22, −14.42, −14.87, −15.47] |
|