| >>> Neural Training Engine Started [TASK: easy_delivery] |
| Episode 0/1000 | Avg Reward: -1.45 | Epsilon: 0.99 (Periodic Save) |
| Episode 50/1000 | Avg Reward: -4.50 | Epsilon: 0.77 (Periodic Save) |
| Episode 100/1000 | Avg Reward: 0.30 | Epsilon: 0.60 (Periodic Save) |
| Episode 150/1000 | Avg Reward: 0.15 | Epsilon: 0.47 (Periodic Save) |
| Episode 200/1000 | Avg Reward: -1.25 | Epsilon: 0.37 (Periodic Save) |
| Episode 250/1000 | Avg Reward: -1.10 | Epsilon: 0.28 (Periodic Save) |
| Episode 300/1000 | Avg Reward: 0.70 | Epsilon: 0.22 (Periodic Save) |
| Episode 350/1000 | Avg Reward: -4.20 | Epsilon: 0.17 (Periodic Save) |
| Episode 400/1000 | Avg Reward: 0.80 | Epsilon: 0.13 (Periodic Save) |
| Episode 450/1000 | Avg Reward: 0.60 | Epsilon: 0.10 (Periodic Save) |
| Episode 500/1000 | Avg Reward: -3.65 | Epsilon: 0.08 (Periodic Save) |
| Episode 550/1000 | Avg Reward: -0.70 | Epsilon: 0.06 (Periodic Save) |
| Episode 600/1000 | Avg Reward: -1.55 | Epsilon: 0.05 (Periodic Save) |
| Episode 650/1000 | Avg Reward: 1.00 | Epsilon: 0.05 (Periodic Save) |
| Episode 700/1000 | Avg Reward: 0.60 | Epsilon: 0.05 (Periodic Save) |
| Episode 750/1000 | Avg Reward: -0.60 | Epsilon: 0.05 (Periodic Save) |
| Episode 800/1000 | Avg Reward: -0.10 | Epsilon: 0.05 (Periodic Save) |
| Episode 850/1000 | Avg Reward: -7.20 | Epsilon: 0.05 (Periodic Save) |
| Episode 900/1000 | Avg Reward: 0.90 | Epsilon: 0.05 (Periodic Save) |
| Episode 950/1000 | Avg Reward: 1.00 | Epsilon: 0.05 (Periodic Save) |
| Training complete. Model saved to data/easy.pth. |
|
|
