CS计算机代考程序代写 # n_rows, n_cols

# n_rows, n_cols
6, 8
# offline time limit
5.0
# online time limit
2.0
# reward target
-18.6
# glide probabilities
0.2, 0.6, 0.2
# super jump probabilities
0.2, 0.3, 0.3, 0.2
# super charge probabilities
0.2, 0.3, 0.3, 0.2
# ladder fall probability
0.2
# collision penalty
1.0
# game over penalty
25.0
# grid data
XXXXXXXX
X XX
XG X
X EX
XXP =JXX
XXXXXXXX