Initial commit
This commit is contained in:
@@ -0,0 +1,276 @@
|
||||
values_k_0: """
|
||||
0.0000 0.0000 0.0000
|
||||
"""
|
||||
|
||||
q_values_k_0_action_north: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_east: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_0_action_south: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_west: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_1: """
|
||||
10.0000 0.0000 0.0000
|
||||
"""
|
||||
|
||||
q_values_k_1_action_north: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_east: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1_action_south: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_2: """
|
||||
10.0000 0.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_2_action_north: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_2_action_south: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_3: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_3_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_3_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_4: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_4_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_4_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_5: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_5_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_5_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_6: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_6_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_6_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_7: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_7_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_7_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_8: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_8_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_8_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_9: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_9_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_9_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_1000: """
|
||||
10.0000 5.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_north: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_east: """
|
||||
illegal -5.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_south: """
|
||||
illegal 2.5000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_west: """
|
||||
illegal 5.0000 illegal
|
||||
"""
|
||||
|
||||
policy: """
|
||||
exit west exit
|
||||
"""
|
||||
|
||||
actions: """
|
||||
north
|
||||
east
|
||||
exit
|
||||
south
|
||||
west
|
||||
"""
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
class: "PrioritizedSweepingValueIterationTest"
|
||||
|
||||
# GridWorld specification
|
||||
# _ is empty space
|
||||
# numbers are terminal states with that value
|
||||
# # is a wall
|
||||
# S is a start state
|
||||
#
|
||||
grid: """
|
||||
10 S -10
|
||||
"""
|
||||
discount: "0.5"
|
||||
noise: "0.0"
|
||||
livingReward: "0.0"
|
||||
epsilon: "0.5"
|
||||
learningRate: "0.1"
|
||||
numExperiences: "100"
|
||||
valueIterations: "1000"
|
||||
iterations: "10000"
|
||||
|
||||
|
||||
@@ -0,0 +1,276 @@
|
||||
values_k_0: """
|
||||
0.0000 0.0000 0.0000
|
||||
"""
|
||||
|
||||
q_values_k_0_action_north: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_east: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_0_action_south: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_0_action_west: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
values_k_1: """
|
||||
10.0000 0.0000 0.0000
|
||||
"""
|
||||
|
||||
q_values_k_1_action_north: """
|
||||
illegal 0.9375 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_east: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1_action_south: """
|
||||
illegal 0.9375 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1_action_west: """
|
||||
illegal 5.6250 illegal
|
||||
"""
|
||||
|
||||
values_k_2: """
|
||||
10.0000 0.0000 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_2_action_north: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_east: """
|
||||
illegal -5.6250 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_2_action_south: """
|
||||
illegal 0.0000 illegal
|
||||
"""
|
||||
|
||||
q_values_k_2_action_west: """
|
||||
illegal 5.6250 illegal
|
||||
"""
|
||||
|
||||
values_k_3: """
|
||||
10.0000 5.6250 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_3_action_north: """
|
||||
illegal 3.1641 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_east: """
|
||||
illegal -4.5703 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_3_action_south: """
|
||||
illegal 3.1641 illegal
|
||||
"""
|
||||
|
||||
q_values_k_3_action_west: """
|
||||
illegal 6.6797 illegal
|
||||
"""
|
||||
|
||||
values_k_4: """
|
||||
10.0000 6.6797 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_4_action_north: """
|
||||
illegal 3.7573 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_east: """
|
||||
illegal -4.3726 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_4_action_south: """
|
||||
illegal 3.7573 illegal
|
||||
"""
|
||||
|
||||
q_values_k_4_action_west: """
|
||||
illegal 6.8774 illegal
|
||||
"""
|
||||
|
||||
values_k_5: """
|
||||
10.0000 6.8774 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_5_action_north: """
|
||||
illegal 3.8686 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_east: """
|
||||
illegal -4.3355 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_5_action_south: """
|
||||
illegal 3.8686 illegal
|
||||
"""
|
||||
|
||||
q_values_k_5_action_west: """
|
||||
illegal 6.9145 illegal
|
||||
"""
|
||||
|
||||
values_k_6: """
|
||||
10.0000 6.9145 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_6_action_north: """
|
||||
illegal 3.8894 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_east: """
|
||||
illegal -4.3285 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_6_action_south: """
|
||||
illegal 3.8894 illegal
|
||||
"""
|
||||
|
||||
q_values_k_6_action_west: """
|
||||
illegal 6.9215 illegal
|
||||
"""
|
||||
|
||||
values_k_7: """
|
||||
10.0000 6.9215 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_7_action_north: """
|
||||
illegal 3.8933 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_east: """
|
||||
illegal -4.3272 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_7_action_south: """
|
||||
illegal 3.8933 illegal
|
||||
"""
|
||||
|
||||
q_values_k_7_action_west: """
|
||||
illegal 6.9228 illegal
|
||||
"""
|
||||
|
||||
values_k_8: """
|
||||
10.0000 6.9228 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_8_action_north: """
|
||||
illegal 3.8941 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_east: """
|
||||
illegal -4.3270 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_8_action_south: """
|
||||
illegal 3.8941 illegal
|
||||
"""
|
||||
|
||||
q_values_k_8_action_west: """
|
||||
illegal 6.9230 illegal
|
||||
"""
|
||||
|
||||
values_k_9: """
|
||||
10.0000 6.9230 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_9_action_north: """
|
||||
illegal 3.8942 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_east: """
|
||||
illegal -4.3269 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_9_action_south: """
|
||||
illegal 3.8942 illegal
|
||||
"""
|
||||
|
||||
q_values_k_9_action_west: """
|
||||
illegal 6.9231 illegal
|
||||
"""
|
||||
|
||||
values_k_1000: """
|
||||
10.0000 6.9231 -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_north: """
|
||||
illegal 3.8942 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_east: """
|
||||
illegal -4.3269 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_exit: """
|
||||
10.0000 illegal -10.0000
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_south: """
|
||||
illegal 3.8942 illegal
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_west: """
|
||||
illegal 6.9231 illegal
|
||||
"""
|
||||
|
||||
policy: """
|
||||
exit west exit
|
||||
"""
|
||||
|
||||
actions: """
|
||||
north
|
||||
east
|
||||
exit
|
||||
south
|
||||
west
|
||||
"""
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
class: "PrioritizedSweepingValueIterationTest"
|
||||
|
||||
# GridWorld specification
|
||||
# _ is empty space
|
||||
# numbers are terminal states with that value
|
||||
# # is a wall
|
||||
# S is a start state
|
||||
#
|
||||
grid: """
|
||||
10 S -10
|
||||
"""
|
||||
discount: "0.75"
|
||||
noise: "0.25"
|
||||
livingReward: "0.0"
|
||||
epsilon: "0.5"
|
||||
learningRate: "0.1"
|
||||
numExperiences: "100"
|
||||
valueIterations: "1000"
|
||||
iterations: "10000"
|
||||
|
||||
|
||||
@@ -0,0 +1,410 @@
|
||||
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 __________
|
||||
"""
|
||||
|
||||
q_values_k_0_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal 0.0000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_0_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal 0.0000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_0_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_0_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal 0.0000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_0_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal 0.0000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ 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
|
||||
__________ -100.0000 0.0000 0.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_1_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal 0.0000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -4.2500 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_1_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -4.2500 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_2: """
|
||||
__________ -100.0000 0.0000 0.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 0.0000 0.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_2_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_2_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_2_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_2_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_2_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_3: """
|
||||
__________ -100.0000 0.0000 0.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 0.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_3_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 0.0000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_3_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -4.2500 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_3_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_3_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_3_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -4.2500 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_4: """
|
||||
__________ -100.0000 -100.0000 0.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 0.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_4_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_4_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_4_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_4_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_4_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_5: """
|
||||
__________ -100.0000 -100.0000 0.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_5_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 0.0000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_5_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -4.2500 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_5_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_5_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_5_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -4.2500 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_6: """
|
||||
__________ -100.0000 -100.0000 -100.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 0.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_6_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_6_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_6_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_6_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_6_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_7: """
|
||||
__________ -100.0000 -100.0000 -100.0000 0.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_7_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 0.0000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_7_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -4.2500 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_7_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_7_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 -76.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_7_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -4.2500 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_8: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 0.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_8_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 -76.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_8_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -8.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_8_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_8_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 -76.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_8_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -8.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_9: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 0.0000 __________
|
||||
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_9_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 -76.5000 0.0000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_9_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -8.5000 -4.2500 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_9_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_9_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -76.5000 -76.5000 -76.5000 -76.5000 -76.5000 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_9_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -8.5000 -8.5000 -8.5000 -8.5000 -4.2500 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
values_k_1000: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 -7.7350 -14.4173 -15.4999 -9.1502 -0.8500 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_north: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -77.0702 -77.4875 -77.5016 -77.1949 -76.4639 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_east: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -19.5292 -20.3575 -15.4999 -9.1502 -0.8500 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_exit: """
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
1.0000 illegal illegal illegal illegal illegal 10.0000
|
||||
__________ -100.0000 -100.0000 -100.0000 -100.0000 -100.0000 __________
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_south: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -77.0702 -77.4875 -77.5016 -77.1949 -76.4639 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
q_values_k_1000_action_west: """
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
illegal -7.7350 -14.4173 -19.5292 -20.3575 -15.4999 illegal
|
||||
__________ illegal illegal illegal illegal illegal __________
|
||||
"""
|
||||
|
||||
policy: """
|
||||
__________ exit exit exit exit exit __________
|
||||
exit west west east east east exit
|
||||
__________ exit exit exit exit exit __________
|
||||
"""
|
||||
|
||||
actions: """
|
||||
north
|
||||
east
|
||||
exit
|
||||
south
|
||||
west
|
||||
"""
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
class: "PrioritizedSweepingValueIterationTest"
|
||||
|
||||
# GridWorld specification
|
||||
# _ is empty space
|
||||
# numbers are terminal states with that value
|
||||
# # is a wall
|
||||
# S is a start state
|
||||
#
|
||||
grid: """
|
||||
# -100 -100 -100 -100 -100 #
|
||||
1 S _ _ _ _ 10
|
||||
# -100 -100 -100 -100 -100 #
|
||||
"""
|
||||
gridName: "bridgeGrid"
|
||||
discount: "0.85"
|
||||
noise: "0.1"
|
||||
livingReward: "0.0"
|
||||
epsilon: "0.5"
|
||||
learningRate: "0.1"
|
||||
numExperiences: "500"
|
||||
valueIterations: "1000"
|
||||
iterations: "10000"
|
||||
|
||||
|
||||
@@ -0,0 +1,544 @@
|
||||
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
|
||||
"""
|
||||
|
||||
@@ -0,0 +1,25 @@
|
||||
class: "PrioritizedSweepingValueIterationTest"
|
||||
|
||||
# GridWorld specification
|
||||
# _ is empty space
|
||||
# numbers are terminal states with that value
|
||||
# # is a wall
|
||||
# S is a start state
|
||||
#
|
||||
grid: """
|
||||
_ _ _ _ _
|
||||
_ # _ _ _
|
||||
_ # 1 # 10
|
||||
S _ _ _ _
|
||||
-10 -10 -10 -10 -10
|
||||
"""
|
||||
discount: "0.9"
|
||||
noise: "0.2"
|
||||
livingReward: "0.0"
|
||||
epsilon: "0.2"
|
||||
learningRate: "0.1"
|
||||
numExperiences: "3000"
|
||||
valueIterations: "1000"
|
||||
iterations: "10000"
|
||||
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
max_points: "3"
|
||||
class: "PassAllTestsQuestion"
|
||||
Reference in New Issue
Block a user