← 实验室

在格子世界里找到路

CPU · Python 3.12.13 · 2.35 s · 2026-10-22 08:53:43 UTC+8

本次运行结果

success_rate1.0
mean_steps6.0
{'start': (0, 0), 'trap': (1, 1), 'goal': (3, 3), 'episodes': 500}
Optimal state values:
 [[0.729 0.777 0.829 0.883]
 [0.777 0.    0.883 0.94 ]
 [0.829 0.883 0.94  1.   ]
 [0.883 0.94  1.    0.   ]]
{'success_rate': 1.0, 'mean_steps': 6.0}
Seed 0 greedy path: [(0, 0), (1, 0), (2, 0), (2, 1), (3, 1), (3, 2), (3, 3)]
Experiment output
46
Optional exercise: fill answer and enable RUN_EXERCISE.
metrics.json
{
  "success_rate": 1.0,
  "mean_steps": 6.0
}