CS计算机代考程序代写 # n_rows, n_cols

# n_rows, n_cols
6, 12
# offline time limit
5.0
# online time limit
1.0
# reward target
-23.9
# glide probabilities
0.2, 0.6, 0.2
# super jump probabilities
0.2, 0.3, 0.3, 0.2
# super charge probabilities
0.1, 0.2, 0.3, 0.4
# ladder fall probability
0.1
# collision penalty
1.0
# game over penalty
500.0
# grid data
XXXXXXXXXXXX
X G G X
X=X X=X
X=P E X=X
XXXXX =X
XXXXXXXXXXXX