Table 4.
Experimental evaluation process on response time comparison.
| Policy | Response_time | Description |
|---|---|---|
| DRLNDT | 7.4250 | Transformer + SAC |
| Baseline | 2.8370 | RNN + SAC |
| Standard SAC | 2.7200 | |
| DRLNDT-n-10 | 7.1830 | Historical state length n = 10 |
| DRLNDT-n-20 | 8.1440 | Historical state length n = 20 |
| DRLNDT-n-30 | 5.7540 | Historical state length n = 30 |
| DRLNDT-n-40 | 7.4040 | Historical state length n = 40 |
| DRLNDT-n-60 | 7.4030 | Historical state length n = 60 |
| DRLNDT-n-70 | 7.4046 | Historical state length n = 70 |
| DRLNDT-n-80 | 7.7540 | Historical state length n = 80 |
| DRLNDT-w-0.125 | 7.4350 | Potential_reward_w = 0.125 |
| DRLNDT-w-0.175 | 7.4130 | Potential_reward_w = 0.175 |
| DRLNDT-w-0.25 | 7.5120 | Potential_reward_w = 0.25 |
| DRLNDT-w-0.5 | 7.3780 | Potential_reward_w = 0.5 |
| Modular Pipi | 1.3000 |