p7px8vou9
/
AI_learning
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'd44f0548d0'
${ noResults }
AI_learning/cs188-projects-master/P3 Reinforcement Learning/test_cases/q5/4-discountgrid.solution

545 lines
25 KiB
Raw Blame History

values_k_0: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
"""
q_values_k_0_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_0_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_0_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_0_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_0_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_1: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 0.0000 0.0000 0.0000 0.0000
"""
q_values_k_1_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_1_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_1_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_1_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-7.2000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_1_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_2: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 -10.0000 0.0000 0.0000 0.0000
"""
q_values_k_2_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_2_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_2_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_2_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_2_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_3: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 -10.0000 -10.0000 0.0000 0.0000
"""
q_values_k_3_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_3_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_3_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_3_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_3_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_4: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 -10.0000 -10.0000 -10.0000 0.0000
"""
q_values_k_4_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_4_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_4_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_4_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -7.2000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_4_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_5: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 0.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_5_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_5_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 -0.9000
illegal illegal illegal illegal illegal
"""
q_values_k_5_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_5_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -7.2000 -7.2000
illegal illegal illegal illegal illegal
"""
q_values_k_5_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 -0.9000
illegal illegal illegal illegal illegal
"""
values_k_6: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 10.0000
0.0000 0.0000 0.0000 0.0000 0.0000
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_6_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.0000 7.2000
illegal illegal illegal illegal illegal
"""
q_values_k_6_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.9000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
q_values_k_6_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_6_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 7.2000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -7.2000 -7.2000
illegal illegal illegal illegal illegal
"""
q_values_k_6_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.9000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_7: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 __________ 10.0000
0.0000 0.0000 0.0000 0.0000 7.2000
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_7_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.0000
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.6480 7.8480
illegal illegal illegal illegal illegal
"""
q_values_k_7_action_east: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.9000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 4.2840 5.1840
illegal illegal illegal illegal illegal
"""
q_values_k_7_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_7_action_south: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 7.2000
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -6.5520 -6.5520
illegal illegal illegal illegal illegal
"""
q_values_k_7_action_west: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 0.9000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_8: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.0000 7.2000
0.0000 __________ 0.0000 __________ 10.0000
0.0000 0.0000 0.0000 0.0000 7.2000
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_8_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 0.6480 0.6480
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.6480 7.8480
illegal illegal illegal illegal illegal
"""
q_values_k_8_action_east: """
0.0000 0.0000 0.0000 0.0000 0.6480
0.0000 __________ 0.0000 5.1840 6.0840
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 4.2840 5.1840
illegal illegal illegal illegal illegal
"""
q_values_k_8_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_8_action_south: """
0.0000 0.0000 0.0000 0.0000 5.1840
0.0000 __________ 0.0000 0.6480 7.8480
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -6.5520 -6.5520
illegal illegal illegal illegal illegal
"""
q_values_k_8_action_west: """
0.0000 0.0000 0.0000 0.0000 0.6480
0.0000 __________ 0.0000 0.0000 0.9000
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_9: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.0000 5.1840 7.2000
0.0000 __________ 0.0000 __________ 10.0000
0.0000 0.0000 0.0000 0.0000 7.2000
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_9_action_north: """
0.0000 0.0000 0.0000 0.0000 0.0000
0.0000 __________ 0.4666 0.6480 1.1146
0.0000 __________ illegal __________ illegal
0.0000 0.0000 0.0000 0.6480 7.8480
illegal illegal illegal illegal illegal
"""
q_values_k_9_action_east: """
0.0000 0.0000 0.0000 0.4666 0.6480
0.0000 __________ 3.7325 5.6506 6.0840
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 4.2840 5.1840
illegal illegal illegal illegal illegal
"""
q_values_k_9_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_9_action_south: """
0.0000 0.0000 0.0000 3.7325 5.1840
0.0000 __________ 0.4666 4.3805 8.3146
0.0000 __________ illegal __________ illegal
-7.2000 -7.2000 -7.2000 -6.5520 -6.5520
illegal illegal illegal illegal illegal
"""
q_values_k_9_action_west: """
0.0000 0.0000 0.0000 0.4666 0.6480
0.0000 __________ 0.0000 0.4666 4.6325
0.0000 __________ illegal __________ illegal
-0.9000 -0.9000 -0.9000 -0.9000 0.0000
illegal illegal illegal illegal illegal
"""
values_k_1000: """
4.4765 5.1665 5.8840 6.6836 7.5087
3.9306 __________ 6.0258 7.5087 8.6547
3.4512 __________ 1.0000 __________ 10.0000
2.9289 2.0045 3.3074 5.7186 8.4777
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_1000_action_north: """
4.0909 4.6523 5.3030 6.0175 6.6836
3.9306 __________ 5.4546 6.1334 6.8610
3.4512 __________ illegal __________ illegal
2.9289 2.0045 1.4151 5.1780 8.4777
illegal illegal illegal illegal illegal
"""
q_values_k_1000_action_east: """
4.4765 5.1665 5.8840 6.6836 6.8610
3.5435 __________ 6.0258 7.5087 7.8072
3.1022 __________ illegal __________ illegal
0.8538 1.6617 3.3074 5.7186 6.1039
illegal illegal illegal illegal illegal
"""
q_values_k_1000_action_exit: """
illegal illegal illegal illegal illegal
illegal __________ illegal illegal illegal
illegal __________ 1.0000 __________ 10.0000
illegal illegal illegal illegal illegal
-10.0000 -10.0000 -10.0000 -10.0000 -10.0000
"""
q_values_k_1000_action_south: """
3.6979 4.6523 5.4051 6.6116 7.5087
3.1924 __________ 1.9381 6.7275 8.6547
2.7300 __________ illegal __________ illegal
-6.7560 -6.6387 -6.5049 -6.1393 -5.9223
illegal illegal illegal illegal illegal
"""
q_values_k_1000_action_west: """
3.9797 4.1530 4.7917 5.5138 6.2669
3.5435 __________ 4.9581 5.6159 6.9820
3.1022 __________ illegal __________ illegal
1.5194 1.3892 0.6332 1.9960 4.1174
illegal illegal illegal illegal illegal
"""
policy: """
east east east east south
north __________ east east south
north __________ exit __________ exit
north north east east north
exit exit exit exit exit
"""
actions: """
north
east
exit
south
west
"""
Reference in new issue View Git Blame Copy Permalink