FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
aima-python/agents.py at master · brainnoopen/aima-python · GitHub
brainnoopen
/
aima-python
Public
forked from
aimacode/aima-python
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
aima-python
/
agents.py
Copy path
More file actions
More file actions
Latest commit
History
History
History
1044 lines (849 loc) · 35.1 KB
Breadcrumbs
aima-python
/
agents.py
Copy path
File metadata and controls
1044 lines (849 loc) · 35.1 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Implement Agents and Environments (Chapters 1-2).
The class hierarchies are as follows:
Thing ## A physical object that can exist in an environment
Agent
Wumpus
Dirt
Wall
...
Environment ## An environment holds objects, runs simulations
XYEnvironment
VacuumEnvironment
WumpusEnvironment
An agent program is a callable instance, taking percepts and choosing actions
SimpleReflexAgentProgram
...
EnvGUI ## A window with a graphical representation of the Environment
EnvToolbar ## contains buttons for controlling EnvGUI
EnvCanvas ## Canvas to display the environment of an EnvGUI
"""
# TO DO:
# Implement grabbing correctly.
# When an object is grabbed, does it still have a location?
# What if it is released?
# What if the grabbed or the grabber is deleted?
# What if the grabber moves?
#
# Speed control in GUI does not have any effect -- fix it.
from
utils
import
distance_squared
,
turn_heading
from
statistics
import
mean
from
ipythonblocks
import
BlockGrid
from
IPython
.
display
import
HTML
,
display
from
time
import
sleep
import
random
import
copy
import
collections
# ______________________________________________________________________________
class
Thing
:
"""This represents any physical object that can appear in an Environment.
You subclass Thing to get the things you want. Each thing can have a
.__name__ slot (used for output only)."""
def
__repr__
(
self
):
return
'<{}>'
.
format
(
getattr
(
self
,
'__name__'
,
self
.
__class__
.
__name__
))
def
is_alive
(
self
):
"""Things that are 'alive' should return true."""
return
hasattr
(
self
,
'alive'
)
and
self
.
alive
def
show_state
(
self
):
"""Display the agent's internal state. Subclasses should override."""
print
(
"I don't know how to show_state."
)
def
display
(
self
,
canvas
,
x
,
y
,
width
,
height
):
"""Display an image of this Thing on the canvas."""
# Do we need this?
pass
class
Agent
(
Thing
):
"""An Agent is a subclass of Thing with one required slot,
.program, which should hold a function that takes one argument, the
percept, and returns an action. (What counts as a percept or action
will depend on the specific environment in which the agent exists.)
Note that 'program' is a slot, not a method. If it were a method,
then the program could 'cheat' and look at aspects of the agent.
It's not supposed to do that: the program can only look at the
percepts. An agent program that needs a model of the world (and of
the agent itself) will have to build and maintain its own model.
There is an optional slot, .performance, which is a number giving
the performance measure of the agent in its environment."""
def
__init__
(
self
,
program
=
None
):
self
.
alive
=
True
self
.
bump
=
False
self
.
holding
=
[]
self
.
performance
=
0
if
program
is
None
or
not
isinstance
(
program
,
collections
.
Callable
):
print
(
"Can't find a valid program for {}, falling back to default."
.
format
(
self
.
__class__
.
__name__
))
def
program
(
percept
):
return
eval
(
input
(
'Percept={}; action? '
.
format
(
percept
)))
self
.
program
=
program
def
can_grab
(
self
,
thing
):
"""Return True if this agent can grab this thing.
Override for appropriate subclasses of Agent and Thing."""
return
False
def
TraceAgent
(
agent
):
"""Wrap the agent's program to print its input and output. This will let
you see what the agent is doing in the environment."""
old_program
=
agent
.
program
def
new_program
(
percept
):
action
=
old_program
(
percept
)
print
(
'{} perceives {} and does {}'
.
format
(
agent
,
percept
,
action
))
return
action
agent
.
program
=
new_program
return
agent
# ______________________________________________________________________________
def
TableDrivenAgentProgram
(
table
):
"""This agent selects an action based on the percept sequence.
It is practical only for tiny domains.
To customize it, provide as table a dictionary of all
{percept_sequence:action} pairs. [Figure 2.7]"""
percepts
=
[]
def
program
(
percept
):
percepts
.
append
(
percept
)
action
=
table
.
get
(
tuple
(
percepts
))
return
action
return
program
def
RandomAgentProgram
(
actions
):
"""An agent that chooses an action at random, ignoring all percepts.
>>> list = ['Right', 'Left', 'Suck', 'NoOp']
>>> program = RandomAgentProgram(list)
>>> agent = Agent(program)
>>> environment = TrivialVacuumEnvironment()
>>> environment.add_thing(agent)
>>> environment.run()
>>> environment.status == {(1, 0): 'Clean' , (0, 0): 'Clean'}
True
"""
return
lambda
percept
:
random
.
choice
(
actions
)
# ______________________________________________________________________________
def
SimpleReflexAgentProgram
(
rules
,
interpret_input
):
"""This agent takes action based solely on the percept. [Figure 2.10]"""
def
program
(
percept
):
state
=
interpret_input
(
percept
)
rule
=
rule_match
(
state
,
rules
)
action
=
rule
.
action
return
action
return
program
def
ModelBasedReflexAgentProgram
(
rules
,
update_state
,
model
):
"""This agent takes action based on the percept and state. [Figure 2.12]"""
def
program
(
percept
):
program
.
state
=
update_state
(
program
.
state
,
program
.
action
,
percept
,
model
)
rule
=
rule_match
(
program
.
state
,
rules
)
action
=
rule
.
action
return
action
program
.
state
=
program
.
action
=
None
return
program
def
rule_match
(
state
,
rules
):
"""Find the first rule that matches state."""
for
rule
in
rules
:
if
rule
.
matches
(
state
):
return
rule
# ______________________________________________________________________________
loc_A
,
loc_B
=
(
0
,
0
), (
1
,
0
)
# The two locations for the Vacuum world
def
RandomVacuumAgent
():
"""Randomly choose one of the actions from the vacuum environment.
>>> agent = RandomVacuumAgent()
>>> environment = TrivialVacuumEnvironment()
>>> environment.add_thing(agent)
>>> environment.run()
>>> environment.status == {(1,0):'Clean' , (0,0) : 'Clean'}
True
"""
return
Agent
(
RandomAgentProgram
([
'Right'
,
'Left'
,
'Suck'
,
'NoOp'
]))
def
TableDrivenVacuumAgent
():
"""[Figure 2.3]"""
table
=
{((
loc_A
,
'Clean'
),):
'Right'
,
((
loc_A
,
'Dirty'
),):
'Suck'
,
((
loc_B
,
'Clean'
),):
'Left'
,
((
loc_B
,
'Dirty'
),):
'Suck'
,
((
loc_A
,
'Dirty'
), (
loc_A
,
'Clean'
)):
'Right'
,
((
loc_A
,
'Clean'
), (
loc_B
,
'Dirty'
)):
'Suck'
,
((
loc_B
,
'Clean'
), (
loc_A
,
'Dirty'
)):
'Suck'
,
((
loc_B
,
'Dirty'
), (
loc_B
,
'Clean'
)):
'Left'
,
((
loc_A
,
'Dirty'
), (
loc_A
,
'Clean'
), (
loc_B
,
'Dirty'
)):
'Suck'
,
((
loc_B
,
'Dirty'
), (
loc_B
,
'Clean'
), (
loc_A
,
'Dirty'
)):
'Suck'
}
return
Agent
(
TableDrivenAgentProgram
(
table
))
def
ReflexVacuumAgent
():
"""A reflex agent for the two-state vacuum environment. [Figure 2.8]
>>> agent = ReflexVacuumAgent()
>>> environment = TrivialVacuumEnvironment()
>>> environment.add_thing(agent)
>>> environment.run()
>>> environment.status == {(1,0):'Clean' , (0,0) : 'Clean'}
True
"""
def
program
(
percept
):
location
,
status
=
percept
if
status
==
'Dirty'
:
return
'Suck'
elif
location
==
loc_A
:
return
'Right'
elif
location
==
loc_B
:
return
'Left'
return
Agent
(
program
)
def
ModelBasedVacuumAgent
():
"""An agent that keeps track of what locations are clean or dirty.
>>> agent = ModelBasedVacuumAgent()
>>> environment = TrivialVacuumEnvironment()
>>> environment.add_thing(agent)
>>> environment.run()
>>> environment.status == {(1,0):'Clean' , (0,0) : 'Clean'}
True
"""
model
=
{
loc_A
:
None
,
loc_B
:
None
}
def
program
(
percept
):
"""Same as ReflexVacuumAgent, except if everything is clean, do NoOp."""
location
,
status
=
percept
model
[
location
]
=
status
# Update the model here
if
model
[
loc_A
]
==
model
[
loc_B
]
==
'Clean'
:
return
'NoOp'
elif
status
==
'Dirty'
:
return
'Suck'
elif
location
==
loc_A
:
return
'Right'
elif
location
==
loc_B
:
return
'Left'
return
Agent
(
program
)
# ______________________________________________________________________________
class
Environment
:
"""Abstract class representing an Environment. 'Real' Environment classes
inherit from this. Your Environment will typically need to implement:
percept: Define the percept that an agent sees.
execute_action: Define the effects of executing an action.
Also update the agent.performance slot.
The environment keeps a list of .things and .agents (which is a subset
of .things). Each agent has a .performance slot, initialized to 0.
Each thing has a .location slot, even though some environments may not
need this."""
def
__init__
(
self
):
self
.
things
=
[]
self
.
agents
=
[]
def
thing_classes
(
self
):
return
[]
# List of classes that can go into environment
def
percept
(
self
,
agent
):
"""Return the percept that the agent sees at this point. (Implement this.)"""
raise
NotImplementedError
def
execute_action
(
self
,
agent
,
action
):
"""Change the world to reflect this action. (Implement this.)"""
raise
NotImplementedError
def
default_location
(
self
,
thing
):
"""Default location to place a new thing with unspecified location."""
return
None
def
exogenous_change
(
self
):
"""If there is spontaneous change in the world, override this."""
pass
def
is_done
(
self
):
"""By default, we're done when we can't find a live agent."""
return
not
any
(
agent
.
is_alive
()
for
agent
in
self
.
agents
)
def
step
(
self
):
"""Run the environment for one time step. If the
actions and exogenous changes are independent, this method will
do. If there are interactions between them, you'll need to
override this method."""
if
not
self
.
is_done
():
actions
=
[]
for
agent
in
self
.
agents
:
if
agent
.
alive
:
actions
.
append
(
agent
.
program
(
self
.
percept
(
agent
)))
else
:
actions
.
append
(
""
)
for
(
agent
,
action
)
in
zip
(
self
.
agents
,
actions
):
self
.
execute_action
(
agent
,
action
)
self
.
exogenous_change
()
def
run
(
self
,
steps
=
1000
):
"""Run the Environment for given number of time steps."""
for
step
in
range
(
steps
):
if
self
.
is_done
():
return
self
.
step
()
def
list_things_at
(
self
,
location
,
tclass
=
Thing
):
"""Return all things exactly at a given location."""
return
[
thing
for
thing
in
self
.
things
if
thing
.
location
==
location
and
isinstance
(
thing
,
tclass
)]
def
some_things_at
(
self
,
location
,
tclass
=
Thing
):
"""Return true if at least one of the things at location
is an instance of class tclass (or a subclass)."""
return
self
.
list_things_at
(
location
,
tclass
)
!=
[]
def
add_thing
(
self
,
thing
,
location
=
None
):
"""Add a thing to the environment, setting its location. For
convenience, if thing is an agent program we make a new agent
for it. (Shouldn't need to override this.)"""
if
not
isinstance
(
thing
,
Thing
):
thing
=
Agent
(
thing
)
if
thing
in
self
.
things
:
print
(
"Can't add the same thing twice"
)
else
:
thing
.
location
=
location
if
location
is
not
None
else
self
.
default_location
(
thing
)
self
.
things
.
append
(
thing
)
if
isinstance
(
thing
,
Agent
):
thing
.
performance
=
0
self
.
agents
.
append
(
thing
)
def
delete_thing
(
self
,
thing
):
"""Remove a thing from the environment."""
try
:
self
.
things
.
remove
(
thing
)
except
ValueError
as
e
:
print
(
e
)
print
(
" in Environment delete_thing"
)
print
(
" Thing to be removed: {} at {}"
.
format
(
thing
,
thing
.
location
))
print
(
" from list: {}"
.
format
([(
thing
,
thing
.
location
)
for
thing
in
self
.
things
]))
if
thing
in
self
.
agents
:
self
.
agents
.
remove
(
thing
)
class
Direction
:
"""A direction class for agents that want to move in a 2D plane
Usage:
d = Direction("down")
To change directions:
d = d + "right" or d = d + Direction.R #Both do the same thing
Note that the argument to __add__ must be a string and not a Direction object.
Also, it (the argument) can only be right or left."""
R
=
"right"
L
=
"left"
U
=
"up"
D
=
"down"
def
__init__
(
self
,
direction
):
self
.
direction
=
direction
def
__add__
(
self
,
heading
):
"""
>>> d = Direction('right')
>>> l1 = d.__add__(Direction.L)
>>> l2 = d.__add__(Direction.R)
>>> l1.direction
'up'
>>> l2.direction
'down'
>>> d = Direction('down')
>>> l1 = d.__add__('right')
>>> l2 = d.__add__('left')
>>> l1.direction == Direction.L
True
>>> l2.direction == Direction.R
True
"""
if
self
.
direction
==
self
.
R
:
return
{
self
.
R
:
Direction
(
self
.
D
),
self
.
L
:
Direction
(
self
.
U
),
}.
get
(
heading
,
None
)
elif
self
.
direction
==
self
.
L
:
return
{
self
.
R
:
Direction
(
self
.
U
),
self
.
L
:
Direction
(
self
.
D
),
}.
get
(
heading
,
None
)
elif
self
.
direction
==
self
.
U
:
return
{
self
.
R
:
Direction
(
self
.
R
),
self
.
L
:
Direction
(
self
.
L
),
}.
get
(
heading
,
None
)
elif
self
.
direction
==
self
.
D
:
return
{
self
.
R
:
Direction
(
self
.
L
),
self
.
L
:
Direction
(
self
.
R
),
}.
get
(
heading
,
None
)
def
move_forward
(
self
,
from_location
):
"""
>>> d = Direction('up')
>>> l1 = d.move_forward((0, 0))
>>> l1
(0, -1)
>>> d = Direction(Direction.R)
>>> l1 = d.move_forward((0, 0))
>>> l1
(1, 0)
"""
x
,
y
=
from_location
if
self
.
direction
==
self
.
R
:
return
(
x
+
1
,
y
)
elif
self
.
direction
==
self
.
L
:
return
(
x
-
1
,
y
)
elif
self
.
direction
==
self
.
U
:
return
(
x
,
y
-
1
)
elif
self
.
direction
==
self
.
D
:
return
(
x
,
y
+
1
)
class
XYEnvironment
(
Environment
):
"""This class is for environments on a 2D plane, with locations
labelled by (x, y) points, either discrete or continuous.
Agents perceive things within a radius. Each agent in the
environment has a .location slot which should be a location such
as (0, 1), and a .holding slot, which should be a list of things
that are held."""
def
__init__
(
self
,
width
=
10
,
height
=
10
):
super
().
__init__
()
self
.
width
=
width
self
.
height
=
height
self
.
observers
=
[]
# Sets iteration start and end (no walls).
self
.
x_start
,
self
.
y_start
=
(
0
,
0
)
self
.
x_end
,
self
.
y_end
=
(
self
.
width
,
self
.
height
)
perceptible_distance
=
1
def
things_near
(
self
,
location
,
radius
=
None
):
"""Return all things within radius of location."""
if
radius
is
None
:
radius
=
self
.
perceptible_distance
radius2
=
radius
*
radius
return
[(
thing
,
radius2
-
distance_squared
(
location
,
thing
.
location
))
for
thing
in
self
.
things
if
distance_squared
(
location
,
thing
.
location
)
<=
radius2
]
def
percept
(
self
,
agent
):
"""By default, agent perceives things within a default radius."""
return
self
.
things_near
(
agent
.
location
)
def
execute_action
(
self
,
agent
,
action
):
agent
.
bump
=
False
if
action
==
'TurnRight'
:
agent
.
direction
+=
Direction
.
R
elif
action
==
'TurnLeft'
:
agent
.
direction
+=
Direction
.
L
elif
action
==
'Forward'
:
agent
.
bump
=
self
.
move_to
(
agent
,
agent
.
direction
.
move_forward
(
agent
.
location
))
# elif action == 'Grab':
# things = [thing for thing in self.list_things_at(agent.location)
# if agent.can_grab(thing)]
# if things:
# agent.holding.append(things[0])
elif
action
==
'Release'
:
if
agent
.
holding
:
agent
.
holding
.
pop
()
def
default_location
(
self
,
thing
):
return
(
random
.
choice
(
self
.
width
),
random
.
choice
(
self
.
height
))
def
move_to
(
self
,
thing
,
destination
):
"""Move a thing to a new location. Returns True on success or False if there is an Obstacle.
If thing is holding anything, they move with him."""
thing
.
bump
=
self
.
some_things_at
(
destination
,
Obstacle
)
if
not
thing
.
bump
:
thing
.
location
=
destination
for
o
in
self
.
observers
:
o
.
thing_moved
(
thing
)
for
t
in
thing
.
holding
:
self
.
delete_thing
(
t
)
self
.
add_thing
(
t
,
destination
)
t
.
location
=
destination
return
thing
.
bump
def
add_thing
(
self
,
thing
,
location
=
(
1
,
1
),
exclude_duplicate_class_items
=
False
):
"""Add things to the world. If (exclude_duplicate_class_items) then the item won't be
added if the location has at least one item of the same class."""
if
(
self
.
is_inbounds
(
location
)):
if
(
exclude_duplicate_class_items
and
any
(
isinstance
(
t
,
thing
.
__class__
)
for
t
in
self
.
list_things_at
(
location
))):
return
super
().
add_thing
(
thing
,
location
)
def
is_inbounds
(
self
,
location
):
"""Checks to make sure that the location is inbounds (within walls if we have walls)"""
x
,
y
=
location
return
not
(
x
<
self
.
x_start
or
x
>=
self
.
x_end
or
y
<
self
.
y_start
or
y
>=
self
.
y_end
)
def
random_location_inbounds
(
self
,
exclude
=
None
):
"""Returns a random location that is inbounds (within walls if we have walls)"""
location
=
(
random
.
randint
(
self
.
x_start
,
self
.
x_end
),
random
.
randint
(
self
.
y_start
,
self
.
y_end
))
if
exclude
is
not
None
:
while
(
location
==
exclude
):
location
=
(
random
.
randint
(
self
.
x_start
,
self
.
x_end
),
random
.
randint
(
self
.
y_start
,
self
.
y_end
))
return
location
def
delete_thing
(
self
,
thing
):
"""Deletes thing, and everything it is holding (if thing is an agent)"""
if
isinstance
(
thing
,
Agent
):
for
obj
in
thing
.
holding
:
super
().
delete_thing
(
obj
)
for
obs
in
self
.
observers
:
obs
.
thing_deleted
(
obj
)
super
().
delete_thing
(
thing
)
for
obs
in
self
.
observers
:
obs
.
thing_deleted
(
thing
)
def
add_walls
(
self
):
"""Put walls around the entire perimeter of the grid."""
for
x
in
range
(
self
.
width
):
self
.
add_thing
(
Wall
(), (
x
,
0
))
self
.
add_thing
(
Wall
(), (
x
,
self
.
height
-
1
))
for
y
in
range
(
1
,
self
.
height
-
1
):
self
.
add_thing
(
Wall
(), (
0
,
y
))
self
.
add_thing
(
Wall
(), (
self
.
width
-
1
,
y
))
# Updates iteration start and end (with walls).
self
.
x_start
,
self
.
y_start
=
(
1
,
1
)
self
.
x_end
,
self
.
y_end
=
(
self
.
width
-
1
,
self
.
height
-
1
)
def
add_observer
(
self
,
observer
):
"""Adds an observer to the list of observers.
An observer is typically an EnvGUI.
Each observer is notified of changes in move_to and add_thing,
by calling the observer's methods thing_moved(thing)
and thing_added(thing, loc)."""
self
.
observers
.
append
(
observer
)
def
turn_heading
(
self
,
heading
,
inc
):
"""Return the heading to the left (inc=+1) or right (inc=-1) of heading."""
return
turn_heading
(
heading
,
inc
)
class
Obstacle
(
Thing
):
"""Something that can cause a bump, preventing an agent from
moving into the same square it's in."""
pass
class
Wall
(
Obstacle
):
pass
# ______________________________________________________________________________
class
GraphicEnvironment
(
XYEnvironment
):
def
__init__
(
self
,
width
=
10
,
height
=
10
,
boundary
=
True
,
color
=
{},
display
=
False
):
"""Define all the usual XYEnvironment characteristics,
but initialise a BlockGrid for GUI too."""
super
().
__init__
(
width
,
height
)
self
.
grid
=
BlockGrid
(
width
,
height
,
fill
=
(
200
,
200
,
200
))
if
display
:
self
.
grid
.
show
()
self
.
visible
=
True
else
:
self
.
visible
=
False
self
.
bounded
=
boundary
self
.
colors
=
color
def
get_world
(
self
):
"""Returns all the items in the world in a format
understandable by the ipythonblocks BlockGrid."""
result
=
[]
x_start
,
y_start
=
(
0
,
0
)
x_end
,
y_end
=
self
.
width
,
self
.
height
for
x
in
range
(
x_start
,
x_end
):
row
=
[]
for
y
in
range
(
y_start
,
y_end
):
row
.
append
(
self
.
list_things_at
([
x
,
y
]))
result
.
append
(
row
)
return
result
"""
def run(self, steps=1000, delay=1):
"" "Run the Environment for given number of time steps,
but update the GUI too." ""
for step in range(steps):
sleep(delay)
if self.visible:
self.reveal()
if self.is_done():
if self.visible:
self.reveal()
return
self.step()
if self.visible:
self.reveal()
"""
def
run
(
self
,
steps
=
1000
,
delay
=
1
):
"""Run the Environment for given number of time steps,
but update the GUI too."""
for
step
in
range
(
steps
):
self
.
update
(
delay
)
if
self
.
is_done
():
break
self
.
step
()
self
.
update
(
delay
)
def
update
(
self
,
delay
=
1
):
sleep
(
delay
)
if
self
.
visible
:
self
.
conceal
()
self
.
reveal
()
else
:
self
.
reveal
()
def
reveal
(
self
):
"""Display the BlockGrid for this world - the last thing to be added
at a location defines the location color."""
self
.
draw_world
()
self
.
grid
.
show
()
self
.
visible
=
True
def
draw_world
(
self
):
self
.
grid
[:]
=
(
200
,
200
,
200
)
world
=
self
.
get_world
()
for
x
in
range
(
0
,
len
(
world
)):
for
y
in
range
(
0
,
len
(
world
[
x
])):
if
len
(
world
[
x
][
y
]):
self
.
grid
[
y
,
x
]
=
self
.
colors
[
world
[
x
][
y
][
-
1
].
__class__
.
__name__
]
def
conceal
(
self
):
"""Hide the BlockGrid for this world"""
self
.
visible
=
False
display
(
HTML
(
''
))
# ______________________________________________________________________________
# Continuous environment
class
ContinuousWorld
(
Environment
):
"""Model for Continuous World"""
def
__init__
(
self
,
width
=
10
,
height
=
10
):
super
().
__init__
()
self
.
width
=
width
self
.
height
=
height
def
add_obstacle
(
self
,
coordinates
):
self
.
things
.
append
(
PolygonObstacle
(
coordinates
))
class
PolygonObstacle
(
Obstacle
):
def
__init__
(
self
,
coordinates
):
"""Coordinates is a list of tuples."""
super
().
__init__
()
self
.
coordinates
=
coordinates
# ______________________________________________________________________________
# Vacuum environment
class
Dirt
(
Thing
):
pass
class
VacuumEnvironment
(
XYEnvironment
):
"""The environment of [Ex. 2.12]. Agent perceives dirty or clean,
and bump (into obstacle) or not; 2D discrete world of unknown size;
performance measure is 100 for each dirt cleaned, and -1 for
each turn taken."""
def
__init__
(
self
,
width
=
10
,
height
=
10
):
super
().
__init__
(
width
,
height
)
self
.
add_walls
()
def
thing_classes
(
self
):
return
[
Wall
,
Dirt
,
ReflexVacuumAgent
,
RandomVacuumAgent
,
TableDrivenVacuumAgent
,
ModelBasedVacuumAgent
]
def
percept
(
self
,
agent
):
"""The percept is a tuple of ('Dirty' or 'Clean', 'Bump' or 'None').
Unlike the TrivialVacuumEnvironment, location is NOT perceived."""
status
=
(
'Dirty'
if
self
.
some_things_at
(
agent
.
location
,
Dirt
)
else
'Clean'
)
bump
=
(
'Bump'
if
agent
.
bump
else
'None'
)
return
(
status
,
bump
)
def
execute_action
(
self
,
agent
,
action
):
agent
.
bump
=
False
if
action
==
'Suck'
:
dirt_list
=
self
.
list_things_at
(
agent
.
location
,
Dirt
)
if
dirt_list
!=
[]:
dirt
=
dirt_list
[
0
]
agent
.
performance
+=
100
self
.
delete_thing
(
dirt
)
else
:
super
().
execute_action
(
agent
,
action
)
if
action
!=
'NoOp'
:
agent
.
performance
-=
1
class
TrivialVacuumEnvironment
(
Environment
):
"""This environment has two locations, A and B. Each can be Dirty
or Clean. The agent perceives its location and the location's
status. This serves as an example of how to implement a simple
Environment."""
def
__init__
(
self
):
super
().
__init__
()
self
.
status
=
{
loc_A
:
random
.
choice
([
'Clean'
,
'Dirty'
]),
loc_B
:
random
.
choice
([
'Clean'
,
'Dirty'
])}
def
thing_classes
(
self
):
return
[
Wall
,
Dirt
,
ReflexVacuumAgent
,
RandomVacuumAgent
,
TableDrivenVacuumAgent
,
ModelBasedVacuumAgent
]
def
percept
(
self
,
agent
):
"""Returns the agent's location, and the location status (Dirty/Clean)."""
return
(
agent
.
location
,
self
.
status
[
agent
.
location
])
def
execute_action
(
self
,
agent
,
action
):
"""Change agent's location and/or location's status; track performance.
Score 10 for each dirt cleaned; -1 for each move."""
if
action
==
'Right'
:
agent
.
location
=
loc_B
agent
.
performance
-=
1
elif
action
==
'Left'
:
agent
.
location
=
loc_A
agent
.
performance
-=
1
elif
action
==
'Suck'
:
if
self
.
status
[
agent
.
location
]
==
'Dirty'
:
agent
.
performance
+=
10
self
.
status
[
agent
.
location
]
=
'Clean'
def
default_location
(
self
,
thing
):
"""Agents start in either location at random."""
return
random
.
choice
([
loc_A
,
loc_B
])
# ______________________________________________________________________________
# The Wumpus World
class
Gold
(
Thing
):
def
__eq__
(
self
,
rhs
):
"""All Gold are equal"""
return
rhs
.
__class__
==
Gold
pass
class
Bump
(
Thing
):
pass
class
Glitter
(
Thing
):
pass
class
Pit
(
Thing
):
pass
class
Breeze
(
Thing
):
pass
class
Arrow
(
Thing
):
pass
class
Scream
(
Thing
):
pass
class
Wumpus
(
Agent
):
screamed
=
False
pass
class
Stench
(
Thing
):
pass
class
Explorer
(
Agent
):
holding
=
[]
has_arrow
=
True
killed_by
=
""
direction
=
Direction
(
"right"
)
def
can_grab
(
self
,
thing
):
"""Explorer can only grab gold"""
return
thing
.
__class__
==
Gold
class
WumpusEnvironment
(
XYEnvironment
):
pit_probability
=
0.2
# Probability to spawn a pit in a location. (From Chapter 7.2)
# Room should be 4x4 grid of rooms. The extra 2 for walls
def
__init__
(
self
,
agent_program
,
width
=
6
,
height
=
6
):
super
().
__init__
(
width
,
height
)
self
.
init_world
(
agent_program
)
def
init_world
(
self
,
program
):
"""Spawn items in the world based on probabilities from the book"""
"WALLS"
self
.
add_walls
()
"PITS"
for
x
in
range
(
self
.
x_start
,
self
.
x_end
):
for
y
in
range
(
self
.
y_start
,
self
.
y_end
):
if
random
.
random
()
<
self
.
pit_probability
:
self
.
add_thing
(
Pit
(), (
x
,
y
),
True
)
self
.
add_thing
(
Breeze
(), (
x
-
1
,
y
),
True
)
self
.
add_thing
(
Breeze
(), (
x
,
y
-
1
),
True
)
self
.
add_thing
(
Breeze
(), (
x
+
1
,
y
),
True
)
self
.
add_thing
(
Breeze
(), (
x
,
y
+
1
),
True
)
"WUMPUS"
w_x
,
w_y
=
self
.
random_location_inbounds
(
exclude
=
(
1
,
1
))
self
.
add_thing
(
Wumpus
(
lambda
x
:
""
), (
w_x
,
w_y
),
True
)
self
.
add_thing
(
Stench
(), (
w_x
-
1
,
w_y
),
True
)
self
.
add_thing
(
Stench
(), (
w_x
+
1
,
w_y
),
True
)
self
.
add_thing
(
Stench
(), (
w_x
,
w_y
-
1
),
True
)
self
.
add_thing
(
Stench
(), (
w_x
,
w_y
+
1
),
True
)
"GOLD"
self
.
add_thing
(
Gold
(),
self
.
random_location_inbounds
(
exclude
=
(
1
,
1
)),
True
)
"AGENT"
self
.
add_thing
(
Explorer
(
program
), (
1
,
1
),
True
)
def
get_world
(
self
,
show_walls
=
True
):
"""Return the items in the world"""
result
=
[]
x_start
,
y_start
=
(
0
,
0
)
if
show_walls
else
(
1
,
1
)
if
show_walls
:
x_end
,
y_end
=
self
.
width
,
self
.
height
else
:
x_end
,
y_end
=
self
.
width
-
1
,
self
.
height
-
1
for
x
in
range
(
x_start
,
x_end
):
row
=
[]
for
y
in
range
(
y_start
,
y_end
):
row
.
append
(
self
.
list_things_at
((
x
,
y
)))
result
.
append
(
row
)
return
result
def
percepts_from
(
self
,
agent
,
location
,
tclass
=
Thing
):
"""Return percepts from a given location,
and replaces some items with percepts from chapter 7."""
thing_percepts
=
{
Gold
:
Glitter
(),
Wall
:
Bump
(),
Wumpus
:
Stench
(),
Pit
:
Breeze
()}
"""Agents don't need to get their percepts"""
thing_percepts
[
agent
.
__class__
]
=
None
"""Gold only glitters in its cell"""
if
location
!=
agent
.
location
:
thing_percepts
[
Gold
]
=
None
result
=
[
thing_percepts
.
get
(
thing
.
__class__
,
thing
)
for
thing
in
self
.
things
if
thing
.
location
==
location
and
isinstance
(
thing
,
tclass
)]
return
result
if
len
(
result
)
else
[
None
]
def
percept
(
self
,
agent
):
"""Return things in adjacent (not diagonal) cells of the agent.
Result format: [Left, Right, Up, Down, Center / Current location]"""
x
,
y
=
agent
.
location
result
=
[]
result
.
append
(
self
.
percepts_from
(
agent
, (
x
-
1
,
y
)))
result
.
append
(
self
.
percepts_from
(
agent
, (
x
+
1
,
y
)))
result
.
append
(
self
.
percepts_from
(
agent
, (
x
,
y
-
1
)))
result
.
append
(
self
.
percepts_from
(
agent
, (
x
,
y
+
1
)))
result
.
append
(
self
.
percepts_from
(
agent
, (
x
,
y
)))
"""The wumpus gives out a loud scream once it's killed."""
wumpus
=
[
thing
for
thing
in
self
.
things
if
isinstance
(
thing
,
Wumpus
)]
if
len
(
wumpus
)
and
not
wumpus
[
0
].
alive
and
not
wumpus
[
0
].
screamed
:
result
[
-
1
].
append
(
Scream
())
wumpus
[
0
].
screamed
=
True
return
result
def
execute_action
(
self
,
agent
,
action
):
"""Modify the state of the environment based on the agent's actions.
Performance score taken directly out of the book."""
if
isinstance
(
agent
,
Explorer
)
and
self
.
in_danger
(
agent
):
return
agent
.
bump
=
False
if
action
==
'TurnRight'
:
agent
.
direction
+=
Direction
.
R
agent
.
performance
-=
1
elif
action
==
'TurnLeft'
:
agent
.
direction
+=
Direction
.
L
agent
.
performance
-=
1
elif
action
==
'Forward'
:
agent
.
bump
=
self
.
move_to
(
agent
,
agent
.
direction
.
move_forward
(
agent
.
location
))
agent
.
performance
-=
1
elif
action
==
'Grab'
:
things
=
[
thing
for
thing
in
self
.
list_things_at
(
agent
.
location
)
if
agent
.
can_grab
(
thing
)]
if
len
(
things
):
print
(
"Grabbing"
,
things
[
0
].
__class__
.
__name__
)
if
len
(
things
):
agent
.
holding
.
append
(
things
[
0
])
agent
.
performance
-=
1
elif
action
==
'Climb'
:
if
agent
.
location
==
(
1
,
1
):
# Agent can only climb out of (1,1)
agent
.
performance
+=
1000
if
Gold
()
in
agent
.
holding
else
0
self
.
delete_thing
(
agent
)
elif
action
==
'Shoot'
:
"""The arrow travels straight down the path the agent is facing"""
if
agent
.
has_arrow
:
arrow_travel
=
agent
.
direction
.
move_forward
(
agent
.
location
)
while
(
self
.
is_inbounds
(
arrow_travel
)):
wumpus
=
[
thing
for
thing
in
self
.
list_things_at
(
arrow_travel
)
if
isinstance
(
thing
,
Wumpus
)]
if
len
(
wumpus
):
wumpus
[
0
].
alive
=
False
break
arrow_travel
=
agent
.
direction
.
move_forward
(
agent
.
location
)
agent
.
has_arrow
=
False
def
in_danger
(
self
,
agent
):
"""Check if Explorer is in danger (Pit or Wumpus), if he is, kill him"""
for
thing
in
self
.
list_things_at
(
agent
.
location
):
if
isinstance
(
thing
,
Pit
)
or
(
isinstance
(
thing
,
Wumpus
)
and
thing
.
alive
):
agent
.
alive
=
False
agent
.
performance
-=
1000
agent
.
killed_by
=
thing
.
__class__
.
__name__
return
True
return
False
def
is_done
(
self
):
"""The game is over when the Explorer is killed
or if he climbs out of the cave only at (1,1)."""
explorer
=
[
agent
for
agent
in
self
.
agents
if
isinstance
(
agent
,
Explorer
)]
if
len
(
explorer
):
if
explorer
[
0
].
alive
:
return
False
else
:
print
(
"Death by {} [-1000]."
.
format
(
explorer
[
0
].
killed_by
))
else
:
print
(
"Explorer climbed out {}."
.
format
(
"with Gold [+1000]!"
if
Gold
()
not
in
self
.
things
else
"without Gold [+0]"
))
return
True
# TODO: Arrow needs to be implemented
# ______________________________________________________________________________
def
compare_agents
(
EnvFactory
,
AgentFactories
,
n
=
10
,
steps
=
1000
):
"""See how well each of several agents do in n instances of an environment.
Pass in a factory (constructor) for environments, and several for agents.
Create n instances of the environment, and run each agent in copies of
each one for steps. Return a list of (agent, average-score) tuples.
>>> environment = TrivialVacuumEnvironment
>>> agents = [ModelBasedVacuumAgent, ReflexVacuumAgent]
>>> result = compare_agents(environment, agents)
>>> performance_ModelBasedVacummAgent = result[0][1]
>>> performance_ReflexVacummAgent = result[1][1]
View remainder of file in raw view
Back
|
FazBrowse Home
|
New Git URL