Research Article
End-to-End Autonomous Exploration with Deep Reinforcement Learning and Intrinsic Motivation
Table 6
Experiment results of learning exploration with fine-tuning method (exist extrinsic reward).
| Environment | Method | Reward | MER (%) | IQRE |
| Maze-1 | ICM + scratch | 584.59 | 100.00 | 7.93 | Ours + scratch | 586.32 | 100.00 | 4.72 | ICM + fine-tuning | 583.74 | 100.00 | 9.13 | Ours + fine-tuning | 586.56 | 100.00 | 7.24 | Maze-2 | ICM + scratch | 567.28 | 100.00 | 8.07 | Ours + scratch | 571.87 | 100.00 | 5.15 | ICM + fine-tuning | 514.63 | 89.46 | N/A | Ours + fine-tuning | 569.44 | 100.00 | 6.83 | Maze-3 | ICM + scratch | 532.27 | 91.64 | N/A | Ours + scratch | 579.65 | 100.00 | 6.54 | ICM + fine-tuning | 483.16 | 82.95 | N/A | Ours + fine-tuning | 542.68 | 92.63 | N/A |
|
|