Maze Navigation on 16x16 Small Mazes pseudo-randomly generated (test)
11Mean Completion TimeSpiral RL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Spiral RLConvergence Mode=Q-learning adaptive threshold, Memory Strategy=Full storage2025.12 | 11 | 100 | |
| Sentinel RLConvergence Mode=Q-learning adaptive threshold, Memory Strategy=Sampling2025.12 | 12 | 100 | |
| Spiral ConvConvergence Mode=Fixed 40% threshold, Memory Strategy=Full storage2025.12 | 12.8 | 100 | |
| Sentinel ConvConvergence Mode=Fixed 40% threshold, Memory Strategy=Sampling2025.12 | 12.8 | 100 | |
| SpiralConvergence Mode=No Convergence, Memory Strategy=Full storage2025.12 | 14.2 | 100 | |
| SentinelConvergence Mode=No Convergence, Memory Strategy=Sampling2025.12 | 14.2 | 100 |