Notes
This function is in beta test. Please help improve it in the issues
here.
Hints
Your answer may be identical to the JOJ answer in the first several lines.
However, you will still get Wrong Answer because the complete output may be longer and there might be errors in the future lines.
Please double check your code to solve this problem and try again.
Your Answer
*** FAIL: ./test_cases/q3/4-question-3.4.test *** Policy does not visit state (4,2) when moving without noise. *** States visited: ['(0,1)', '(0,2)', '(0,3)', '(0,4)'] *** Student policy: *** N N N N N *** N . N N N *** N . X . X *** N N N N N *** X X X X X *** Legend: N,S,E,W at states which move north etc, X at states which exit, *** . at states where policy not defined *** Gridworld: *** _ _ _ _ _ *** _ # _ _ _ *** _ # 1 # 10 *** S _ _ _ _ *** -10 -10 -10 -10 -10 *** Legend: # wall, _ empty, S start, numbers terminal states with that reward.
JOJ Answer
*** PASS: ./test_cases/q3/4-question-3.4.test