T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
in
g
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
19
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
93
1
~
9
38
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
9
i3
.
1
8
3
1
9
931
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Dia
lo
g
ue ma
na
g
ement using
reinfo
rcement
learning
B
ina
s
hir R
o
f
i’
a
h
,
H
a
nif
F
a
kh
rurr
o
j
a
,
Ca
rma
di M
a
chbu
b
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
a
n
d
In
f
o
rm
a
ti
c
s,
In
sti
tu
t
Tek
n
o
lo
g
i
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
4
,
2
0
2
0
R
ev
is
ed
Oct
3
,
2
0
2
0
Acc
ep
ted
Oct
1
4
,
2
0
2
0
Dia
lo
g
u
e
h
a
s
b
e
e
n
wid
e
l
y
u
se
d
fo
r
v
e
rb
a
l
c
o
m
m
u
n
ica
ti
o
n
b
e
twe
e
n
h
u
m
a
n
a
n
d
r
o
b
o
t
i
n
tera
c
ti
o
n
,
su
c
h
a
s
a
ss
istan
t
ro
b
o
t
in
h
o
sp
it
a
l
.
Ho
we
v
e
r,
th
is
r
o
b
o
t
wa
s
u
su
a
ll
y
li
m
it
e
d
b
y
p
re
d
e
term
in
e
d
d
ial
o
g
u
e
,
so
i
t
will
b
e
d
iffi
c
u
lt
t
o
u
n
d
e
rsta
n
d
n
e
w
wo
r
d
s
fo
r
n
e
w
d
e
si
re
d
g
o
a
l.
I
n
th
is
p
a
p
e
r,
we
d
isc
u
ss
e
d
c
o
n
v
e
rsa
ti
o
n
i
n
In
d
o
n
e
sia
n
o
n
e
n
terta
in
m
e
n
t,
m
o
ti
v
a
ti
o
n
,
e
m
e
rg
e
n
c
y
,
a
n
d
h
e
lp
i
n
g
with
k
n
o
wle
d
g
e
g
ro
wi
n
g
m
e
th
o
d
.
We p
ro
v
id
e
d
m
p
3
a
u
d
i
o
fo
r
m
u
sic
,
fa
iry
tale
,
c
o
m
e
d
y
re
q
u
e
st,
a
n
d
m
o
ti
v
a
ti
o
n
.
T
h
e
e
x
e
c
u
ti
o
n
ti
m
e
fo
r
th
is
re
q
u
e
st
wa
s
3
.
7
4
m
s
o
n
a
v
e
ra
g
e
.
In
e
m
e
rg
e
n
c
y
sit
u
a
ti
o
n
,
p
a
ti
e
n
t
a
b
le
to
a
sk
ro
b
o
t
t
o
c
a
ll
th
e
n
u
rse
.
R
o
b
o
t
will
re
c
o
rd
c
o
m
p
lai
n
t
o
f
p
a
i
n
a
n
d
i
n
f
o
rm
n
u
rse
.
F
ro
m
7
e
m
e
rg
e
n
c
y
re
p
o
rts,
a
ll
c
o
m
p
lain
ts
we
re
su
c
c
e
ss
fu
ll
y
sa
v
e
d
o
n
d
a
tab
a
se
.
In
h
e
l
p
in
g
c
o
n
v
e
rsa
ti
o
n
,
r
o
b
o
t
will
wa
lk
t
o
p
ick
u
p
b
e
l
o
n
g
in
g
s
o
f
p
a
ti
e
n
t.
O
n
c
e
th
e
ro
b
o
t
d
i
d
n
o
t
u
n
d
e
rsta
n
d
with
p
a
ti
e
n
t’s
c
o
n
v
e
rsa
ti
o
n
,
ro
b
o
t
will
a
sk
u
n
ti
l
i
t
u
n
d
e
rsta
n
d
s.
F
r
o
m
a
sk
in
g
c
o
n
v
e
rsa
ti
o
n
,
k
n
o
wle
d
g
e
e
x
p
a
n
d
s
fro
m
2
to
1
0
,
wi
th
lea
rn
i
n
g
e
x
e
c
u
ti
o
n
fr
o
m
1
4
0
5
m
s to
3
4
9
0
m
s.
S
ARSA
wa
s
fa
ste
r
to
wa
rd
s
ste
a
d
y
sta
te
b
e
c
a
u
se
o
f
h
ig
h
e
r
c
u
m
u
lativ
e
re
wa
rd
s.
Q
-
l
e
a
rn
in
g
a
n
d
S
ARSA
we
re
a
c
h
ie
v
e
d
d
e
sir
e
d
o
b
jec
t
wi
th
i
n
2
0
0
e
p
iso
d
e
s.
I
t
c
o
n
c
l
u
d
e
s
th
a
t
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
(
RL
)
m
e
th
o
d
t
o
o
v
e
rc
o
m
e
ro
b
o
t
k
n
o
wle
d
g
e
li
m
it
a
ti
o
n
in
a
c
h
iev
in
g
n
e
w d
ialo
g
u
e
g
o
a
l
f
o
r
p
a
ti
e
n
t
a
ss
istan
t
we
re
a
c
h
iev
e
d
.
K
ey
w
o
r
d
s
:
Dialo
g
u
e
m
an
a
g
em
en
t
Hu
m
an
-
r
o
b
o
t
i
n
ter
ac
tio
n
Kn
o
wled
g
e
g
r
o
win
g
R
ein
f
o
r
ce
m
en
t le
ar
n
i
n
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Han
if
Fak
h
r
u
r
r
o
ja
Sch
o
o
l o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
an
d
I
n
f
o
r
m
atics (
SEE
I
)
I
n
s
titu
t T
ek
n
o
lo
g
i Ban
d
u
n
g
Gan
esh
a
No
.
1
0
,
C
o
b
lo
n
g
,
B
an
d
u
n
g
,
J
awa
B
ar
at
4
0
1
3
2
,
I
n
d
o
n
esia
E
m
a
il:
h
an
i0
0
2
@
lip
i.g
o
.
id
1.
I
NT
RO
D
UCT
I
O
N
B
etac
o
r
o
n
av
ir
u
s
SAR
S
-
C
o
V
-
2
o
r
C
o
v
id
-
1
9
o
u
t
b
r
ea
k
is
cu
r
r
en
tly
a
f
f
ec
tin
g
alm
o
s
t
all
o
f
th
e
wo
r
ld
with
a
to
tal
o
f
5
0
3
,
2
0
3
p
eo
p
le
in
f
ec
ted
o
r
co
n
f
ir
m
e
d
p
o
s
i
tiv
e,
an
d
2
2
,
3
4
0
o
f
t
h
em
d
ie
d
as
o
f
Ma
r
ch
2
6
,
2
0
2
0
[
1
]
.
Sin
ce
1
1
Ma
r
c
h
2
0
2
0
,
its
s
tatu
s
h
as
ch
a
n
g
ed
to
a
p
an
d
em
ic.
O
n
e
o
f
th
e
co
n
d
itio
n
s
f
o
r
a
p
a
n
d
em
ic
is
th
e
ex
p
lo
s
io
n
o
f
s
p
r
ea
d
o
r
th
e
h
ig
h
n
u
m
b
er
o
f
ca
s
es
th
at
o
cc
u
r
in
a
s
h
o
r
t
p
er
i
o
d
[
2
]
.
T
o
r
ed
u
ce
s
ig
n
if
ican
t
tr
an
s
m
is
s
io
n
r
ate,
th
e
m
ild
-
s
y
m
p
to
m
p
atien
t
m
u
s
t
b
e
is
o
lated
in
th
e
h
o
s
p
ital
u
n
til
h
ea
led
,
wh
ich
lead
s
to
s
tr
ess
[
3
]
.
T
h
e
latest
d
ev
elo
p
m
en
ts
r
eg
ar
d
i
n
g
co
m
p
an
io
n
/a
s
s
is
tan
ts
h
ip
r
o
b
o
ts
h
av
e
b
ee
n
ca
r
r
ied
o
u
t
[
4
]
,
in
o
r
d
er
to
s
u
p
p
o
r
t
th
e
m
e
n
tal
h
e
alth
o
f
p
atien
ts
,
o
n
e
o
f
th
em
is
Sil
b
o
t
wh
ich
h
as
6
ac
ti
v
ities
s
u
ch
as
wa
k
in
g
th
e
p
atien
t,
ch
ec
k
in
g
th
e
m
o
o
d
,
r
e
m
in
d
in
g
d
u
r
in
g
m
ed
itatio
n
,
c
h
ec
k
in
g
s
af
ety
,
h
elp
i
n
g
th
er
a
p
y
,
an
d
em
er
g
en
cies.
Sil
b
o
t w
ill ca
r
e
f
o
r
m
ild
-
d
em
e
n
tia
p
atien
ts
[
5
]
.
Hu
m
an
-
r
o
b
o
t
in
ter
a
ctio
n
(
H
R
I
)
aim
s
f
o
r
ex
ten
d
in
g
r
o
b
o
t
f
u
n
ctio
n
ality
b
y
m
ak
i
n
g
n
atu
r
al
co
m
m
u
n
icatio
n
with
h
u
m
an
[
6
]
.
T
h
ey
[
7
]
in
t
r
o
d
u
ce
alg
o
r
ith
m
f
r
o
m
lear
n
in
g
r
e
war
d
an
d
h
u
m
a
n
sy
n
ch
r
o
n
o
u
s
ly
.
T
h
e
f
le
x
ib
ilit
y
wo
u
ld
g
ain
f
r
o
m
s
im
u
ltan
e
o
u
s
lear
n
in
g
;
it
g
iv
es
a
t
r
ain
e
r
ab
ilit
y
to
g
o
i
n
as
d
esire
d
an
d
u
p
d
ate
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
r
ewa
r
d
w
h
er
ea
s
it
is
s
till
in
p
r
o
g
r
ess
.
T
h
e
y
[
8
]
in
tr
o
d
u
ce
lea
r
n
in
g
s
ce
n
ar
io
co
m
b
i
n
atio
n
b
etwe
e
n
p
r
ac
tice
an
d
en
d
-
u
s
er
c
r
itiq
u
e,
p
r
ac
tice
g
i
v
es
ac
tu
al
-
wo
r
ld
ex
p
er
ien
ce
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
3
,
J
u
n
e
2
0
2
1
:
93
1
-
9
38
932
en
d
-
u
s
er
/h
u
m
an
c
r
itiq
u
e
wh
e
th
er
g
o
o
d
o
r
b
ad
la
b
el
as
i
n
p
u
t
f
o
r
l
o
s
s
f
u
n
ctio
n
o
r
u
n
ex
p
ec
ted
v
alu
e
o
f
ca
n
d
id
ate
p
o
licies.
T
o
b
u
ild
n
atu
r
al
co
m
m
u
n
icatio
n
b
etwe
en
h
u
m
an
an
d
r
o
b
o
t
f
o
r
ass
is
tan
ts
h
ip
s
,
o
u
r
r
esear
ch
team
h
as
p
r
io
r
wo
r
k
s
s
u
ch
as
s
p
ee
c
h
r
ec
o
g
n
itio
n
[
9
]
,
u
n
clea
r
p
r
o
n
u
n
ciatio
n
[
1
0
]
,
r
o
b
o
t
w
alk
in
g
an
d
p
atter
n
g
en
er
ato
r
[
1
1
,
1
2
]
,
r
o
b
o
t
p
ath
p
lan
n
in
g
[
1
3
]
,
s
p
ee
ch
a
n
d
g
estu
r
e
r
ec
o
g
n
itio
n
[
1
4
]
,
m
u
ltimo
d
al
in
ter
ac
tio
n
[
1
5
]
an
d
r
u
le
-
b
ased
/s
ce
n
ar
io
d
ialo
g
u
e
m
a
n
ag
em
en
t
[
1
6
]
.
Ho
we
v
er
th
e
p
r
o
b
lem
o
f
r
u
le
-
b
ased
is
u
n
ab
le
to
f
o
llo
w
d
ialo
g
u
e
d
ev
el
o
p
m
en
t,
s
o
th
e
p
o
s
s
ib
ilit
y
o
f
s
ce
n
ar
io
m
is
m
atch
is
g
etti
n
g
b
ig
g
er
,
o
n
ce
t
h
e
r
o
b
o
t
d
o
es
n
o
t
u
n
d
er
s
tan
d
,
n
o
o
th
e
r
ch
o
ice
f
o
r
th
is
m
eth
o
d
b
esid
es
en
d
th
e
d
ialo
g
u
e
a
n
d
g
iv
es
g
en
e
r
ic
an
s
wer
s
lik
e
"I
d
o
n
'
t
u
n
d
er
s
tan
d
y
o
u
r
c
o
m
m
an
d
s
"
[
1
7
]
.
T
h
is
p
ap
e
r
tak
es
p
ar
t
o
n
o
v
er
co
m
e
r
o
b
o
t
k
n
o
wled
g
e
li
m
itatio
n
to
ac
h
iev
e
n
ew
g
o
al
th
r
o
u
g
h
f
lex
ib
le
d
ial
o
g
u
e.
W
e
p
r
o
p
o
s
e
r
o
b
o
t
ask
i
n
g
m
eth
o
d
to
g
ath
e
r
n
ew
k
n
o
wled
g
e
f
r
o
m
h
u
m
a
n
f
ee
d
b
ac
k
th
r
o
u
g
h
co
n
v
er
s
atio
n
.
T
h
e
r
o
b
o
t
d
o
es
n
o
t
s
to
p
i
m
m
ed
i
ately
b
ec
au
s
e
o
f
n
o
t
u
n
d
er
s
tan
d
,
b
u
t
it
will
ask
f
ir
s
t
an
d
g
ath
e
r
n
ew
k
n
o
w
led
g
e
with
g
o
al
t
o
tak
e
p
atien
t
b
elo
n
g
in
g
s
.
W
e
also
p
r
o
v
id
e
en
ter
tain
m
en
t
an
d
em
er
g
en
cy
r
eq
u
est
to
co
m
p
le
m
en
t
p
atien
t
n
ee
d
s
.
T
h
is
p
ap
e
r
wo
u
ld
d
is
cu
s
s
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
b
o
t
h
in
u
n
d
er
s
tan
d
in
g
an
d
g
en
e
r
atio
n
with
d
if
f
er
e
n
t
s
u
b
-
se
ctio
n
,
d
ialo
g
u
e
m
a
n
ag
em
en
t
m
et
h
o
d
,
also
th
e
h
ar
d
war
e
s
et
-
u
p
f
o
r
r
o
b
o
t.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Na
t
ura
l
la
ng
ua
g
e
un
dersta
nd
ing
T
h
is
p
ap
er
wo
u
l
d
f
o
cu
s
o
n
g
o
al
-
d
r
iv
e
n
d
ialo
g
u
e.
T
h
e
f
u
n
ctio
n
o
f
n
at
u
r
al
lan
g
u
ag
e
u
n
d
er
s
tan
d
in
g
(
NL
U
)
ar
e
ex
tr
ac
tin
g
th
e
r
aw
v
o
ice
u
n
til
s
y
s
tem
g
o
t
th
e
in
f
o
r
m
atio
n
n
ee
d
ed
,
an
d
p
r
o
v
id
e
d
ialo
g
u
e
in
f
o
r
m
atio
n
f
o
r
d
ialo
g
u
e
m
a
n
ag
em
en
t.
NL
U
in
clu
d
es
id
e
n
tific
atio
n
o
f
d
o
m
ain
a
n
d
in
ten
t,
also
s
em
an
tic
p
ar
s
in
g
[
1
8
]
.
T
ex
t
will
g
et
s
ev
er
al
p
r
o
ce
s
s
es:
Sto
p
wo
r
d
p
r
o
ce
s
s
to
r
em
o
v
e
u
n
n
ec
ess
ar
y
s
u
ch
as
c
o
m
m
o
n
wo
r
d
s
.
Par
t
o
f
s
p
ee
ch
(
POS)
t
ag
g
in
g
p
r
o
ce
s
s
to
g
e
t
g
r
am
m
a
r
tag
with
POSt
ag
_
id
n
a
n
d
u
s
e
I
n
d
o
n
esian
tag
s
et
at
[
1
9
]
.
W
e
f
o
cu
s
ed
o
n
ta
g
VB
(
v
er
b
)
,
NN
(
n
o
u
n
)
,
an
d
C
D
(
ca
r
d
in
al
n
u
m
b
e
r
)
.
W
e
u
s
e
I
n
d
o
n
esia
T
nt
-
T
ag
g
e
r
f
o
r
POS
tag
m
eth
o
d
an
d
I
n
d
o
n
esia
I
DPOSTAG
co
r
p
u
s
f
r
o
m
[
2
0
]
.
Fo
llo
we
d
b
y
s
tem
m
in
g
p
r
o
ce
s
s
to
g
et
r
o
o
t
wo
r
d
b
y
r
e
m
o
v
in
g
th
e
af
f
ix
[
2
1
]
.
E
n
d
e
d
with
s
to
r
in
g
p
r
o
ce
s
s
u
s
in
g
J
av
aScr
ip
t
Ob
ject
No
tatio
n
(
J
SON)
f
o
r
m
at
.
2
.
2
.
Dia
lo
g
ue
ma
na
g
em
ent
Dialo
g
u
e
m
an
ag
e
m
en
t
(
DM
)
co
n
s
is
ts
o
f
s
tate
tr
ac
k
in
g
an
d
g
en
e
r
ate
s
ac
tio
n
.
Ap
p
r
o
ac
h
es
f
o
r
d
ialo
g
u
e
m
an
a
g
em
en
t
p
r
o
b
le
m
s
ar
e
g
r
ap
h
-
b
ased
d
ialo
g
ue
,
f
r
am
e
-
b
ased
d
ialo
g
ue
,
s
tatis
t
ical
ap
p
r
o
ac
h
[
2
2
]
.
Hu
m
an
in
v
o
lv
e
m
en
t in
DM
f
r
am
ewo
r
k
h
as b
ee
n
s
u
cc
ess
f
u
lly
ca
r
r
ied
o
u
t in
p
r
ev
io
u
s
s
tu
d
i
es
[
2
3
]
.
T
h
e
r
ewa
r
d
as
f
ee
d
b
ac
k
f
r
o
m
ex
p
e
r
tis
e
(
c
an
b
e
f
o
r
m
ed
in
n
eg
ativ
e
o
r
p
o
s
itiv
e
r
ewa
r
d
s
)
was
g
iv
en
to
o
p
tim
ize
p
o
licy
o
n
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
(
R
L
)
i
n
[
2
4
]
.
R
L
was
s
till
th
e
m
ain
in
s
tr
u
m
en
t
f
o
r
DM
.
R
L
is
cu
r
r
en
t
m
ai
n
s
tr
ea
m
tech
n
o
lo
g
y
in
o
r
d
er
to
s
o
lv
e
r
e
al
-
wo
r
ld
p
r
o
b
lem
with
lar
g
e
-
s
ca
le
b
elief
s
tate
s
p
ac
e
[
1
8
]
.
B
ef
o
r
e
R
L
ca
n
b
e
ex
p
lain
ed
,
it
n
ec
ess
ar
y
to
u
n
d
er
s
tan
d
b
asic
co
m
p
o
n
en
ts
u
s
ed
.
A
lear
n
er
ca
lled
a
n
ag
en
t
in
R
L
s
tu
d
ies
it
s
b
eh
av
io
r
b
y
s
elec
t
ac
tio
n
s
in
an
en
v
i
r
o
n
m
en
t
[
2
5
]
.
At
ea
ch
tim
e,
t
h
e
ag
en
t
r
ec
eiv
es
a
r
ep
r
esen
tatio
n
o
f
s
tate
,
wh
ile
∈
,
wh
er
e
is
s
tates.
T
h
e
ag
en
t
p
i
ck
u
p
s
an
ac
tio
n
,
wh
ile
∈
,
wh
er
e
is
a
s
et
o
f
p
o
s
s
ib
le
ac
tio
n
s
th
at
th
e
ag
e
n
t
ca
n
tak
e.
As
th
e
r
etu
r
n
o
f
its
ac
tio
n
,
th
e
ag
en
t
r
ec
eiv
es
r
ewa
r
d
,
wh
ile
∈
,
an
d
g
o
es
to
n
ew
s
tate
s′
.
is
lear
n
i
n
g
r
ate,
γ
is
a
d
is
co
u
n
t
f
ac
to
r
,
an
d
is
p
o
licy
th
at
d
e
f
in
es
h
o
w
an
ag
en
t
r
esp
o
n
s
e
f
r
o
m
a
s
p
ec
if
ic
s
tate.
T
h
e
aim
o
f
an
ag
en
t
is
s
elec
t
in
g
th
e
o
p
tim
al
ac
tio
n
s
b
y
m
ax
im
izin
g
its
cu
m
u
lativ
e
d
is
co
u
n
ted
r
ewa
r
d
.
I
n
th
is
p
ap
e
r
,
we
u
s
e
R
L
with
tem
p
o
r
al
d
if
f
er
e
n
c
e
(
T
D)
lear
n
in
g
m
eth
o
d
.
T
D
le
ar
n
in
g
is
a
f
u
s
io
n
o
f
two
b
en
ef
its
f
r
o
m
Mo
n
te
C
ar
lo
an
d
d
y
n
am
ic
p
r
o
g
r
am
m
in
g
as
s
h
o
wn
in
(
3
)
,
an
d
(
4
)
.
On
o
n
e
s
id
e,
Mo
n
t
e
C
ar
lo
m
eth
o
d
s
h
av
e
n
o
m
o
d
el
o
f
en
v
ir
o
n
m
en
t’
s
d
y
n
am
ics
as
s
h
o
wn
in
(
1
)
,
s
o
T
D
lear
n
s
f
r
o
m
r
aw
ex
p
er
ien
ce
.
On
th
e
o
th
er
s
id
e,
d
y
n
am
ic
p
r
o
g
r
am
m
in
g
(
2
)
th
at
n
o
n
ee
d
waitin
g
u
n
til
th
e
f
in
al
o
u
tco
m
e,
s
o
T
D
ab
le
to
u
p
d
ate
esti
m
ates b
ased
o
n
p
a
r
tially
lear
n
ed
esti
m
atio
n
[
2
6
]
.
R
ec
all
Mo
n
te
C
ar
lo
:
:
(
)
←
(
)
+
[
(
)
−
(
)
]
,
=
1
(
)
(
1
)
R
ec
all
d
y
n
am
ic
p
r
o
g
r
am
m
i
n
g
:
:
(
)
=
[
+
1
+
(
+
1
)
|
=
]
,
(
2
)
T
D
to
m
ak
e
an
u
p
d
ate
(
)
←
(
)
,
Giv
en
(
,
,
,
′
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dia
lo
g
u
e
ma
n
a
g
eme
n
t
u
s
in
g
r
ein
fo
r
ce
men
t le
a
r
n
in
g
(
B
in
a
s
h
ir
R
o
fi’a
h
)
933
(
)
=
(
1
−
)
(
)
+
[
+
(
′
)
]
⏟
(
3
)
(
)
=
(
)
+
[
+
(
′
)
−
(
)
]
⏟
(
4
)
T
h
e
v
alu
e
f
u
n
ctio
n
u
s
u
ally
al
s
o
ca
lled
as
s
ta
te
-
v
alu
e
f
u
n
cti
o
n
(
)
is
th
e
to
tal
am
o
u
n
t
o
f
ex
p
ec
ted
r
ewa
r
d
s
th
at
an
ag
en
t
ca
n
co
llect
f
r
o
m
th
at
s
tate
to
th
e
en
d
o
f
t
h
e
ep
is
o
d
e.
T
h
e
ac
tio
n
-
v
al
u
e
f
u
n
ctio
n
(
,
)
is
to
tal
am
o
u
n
t
o
f
e
x
p
ec
ted
r
e
war
d
s
o
f
tak
i
n
g
a
n
ac
tio
n
f
r
o
m
th
e
s
tate
u
n
til
t
h
e
en
d
o
f
th
e
ep
is
o
d
e.
T
h
e
way
ag
en
t
lear
n
s
t
h
e
b
est
p
o
licy
c
alled
u
p
d
ate
p
o
licy
,
an
d
th
e
way
ag
en
t
b
eh
a
v
es
ca
lled
b
e
h
av
io
r
p
o
licy
.
I
n
th
is
p
ap
er
,
we
also
im
p
lem
en
t two
T
D
lear
n
in
g
m
et
h
o
d
s
th
at
ar
e
o
f
f
an
d
o
n
p
o
licy
(
Q
-
l
e
ar
n
in
g
an
d
SAR
SA)
.
2
.
2
.
1
.
Q
-
l
ea
rning
Ab
s
o
lu
te
p
o
licy
is
u
s
ed
b
y
a
g
en
t
in
Q
-
le
ar
n
in
g
to
lear
n
o
p
tim
al
p
o
licy
,
o
n
th
e
o
th
e
r
h
an
d
,
a
g
en
t
b
eh
av
es
with
o
th
er
p
o
licy
.
B
e
ca
u
s
e
th
e
b
e
h
av
io
r
p
o
licy
is
d
if
f
er
e
n
t
f
r
o
m
u
p
d
ate
p
o
licy
,
s
o
Q
-
le
ar
n
i
n
g
is
ca
teg
o
r
ized
as o
f
f
-
p
o
licy
T
D
c
o
n
tr
o
l.
Q
-
v
alu
e
o
f
Q
-
le
ar
n
in
g
is
s
h
o
wn
in
(
5
)
.
(
,
)
←
(
,
)
+
[
+
(
′
,
)
−
(
,
)
]
(
5
)
Fro
m
(
5
)
we
h
av
e
k
n
o
wn
th
a
t
u
p
d
ate
p
o
licy
(
′
,
)
is
d
if
f
er
en
t
f
r
o
m
b
e
h
av
io
r
p
o
licy
(
,
)
.
W
e
u
s
e
p
s
eu
d
o
co
d
e
f
r
o
m
[
2
6
]
to
im
p
lem
en
t Q
-
le
ar
n
i
n
g
in
o
u
r
p
y
th
o
n
c
o
d
e
as sh
o
wn
i
n
Fig
u
r
e
1
(
a)
.
2
.
2
.
2
.
Sta
t
e
-
a
ct
io
n
-
re
wa
rd
-
s
t
a
t
e
-
a
c
t
io
n
(
SARSA)
Ag
en
t in
SAR
SA le
ar
n
s
o
p
tim
al
p
o
licy
an
d
b
eh
av
es with
th
e
s
am
e
p
o
licy
.
B
ec
au
s
e
th
e
u
p
d
ate
p
o
licy
an
d
b
e
h
av
io
r
p
o
licy
a
r
e
s
im
ilar
,
s
o
SAR
SA is ca
teg
o
r
ized
as
o
n
-
p
o
licy
.
Q
-
Valu
e
o
f
SAR
SA
is
s
h
o
wn
in
(
6
)
.
(
,
)
←
(
,
)
+
[
+
(
′
,
′
)
−
(
,
)
]
(
6
)
Fro
m
(
6
)
we
k
n
o
w
th
at
u
p
d
at
e
p
o
licy
(
′
,
′
)
an
d
b
eh
a
v
io
r
p
o
licy
(
,
)
also
f
r
o
m
p
s
eu
d
o
co
d
e
b
elo
w,
we
k
n
o
w
th
at
←
′
an
d
←
′
m
ea
n
s
u
p
d
ate
p
o
licy
is
th
e
b
eh
a
v
io
r
p
o
licy
.
W
e
u
s
e
p
s
eu
d
o
co
d
e
[
2
6
]
to
im
p
lem
en
t SAR
SA in
o
u
r
p
y
t
h
o
n
co
d
e
a
s
s
h
o
wn
in
Fig
u
r
e
1
(
b
)
.
E
s
tim
ate
≈
∗
with
Q
-
lear
n
in
g
(
o
f
f
-
p
o
licy
T
D
co
n
tr
o
l)
E
s
tim
ate
≈
∗
with
SAR
S
A
(
o
n
-
p
o
licy
T
D
c
o
n
tr
o
l)
I
n
itialize
(
,
)
,
f
o
r
all
∈
,
∈
(
)
Repea
t
(
ea
ch
ep
is
o
d
e
)
:
I
n
itialize
Repea
t
(
ea
ch
s
tep
)
:
C
h
o
o
s
e
f
r
o
m
u
s
in
g
d
er
iv
ed
f
r
o
m
T
ak
e
ac
tio
n
,
o
b
s
er
v
e
,
′
(
,
)
←
(
,
)
+
[
+
(
′
,
)
−
(
,
)
]
←
′
Unt
il
i
s
ter
m
in
al
I
n
itialize
(
,
)
,
f
o
r
all
∈
,
∈
(
)
Repea
t
(
ea
ch
ep
is
o
d
e
)
:
I
n
itialize
C
h
o
o
s
e
f
r
o
m
u
s
in
g
d
er
iv
ed
f
r
o
m
Repea
t
(
ea
ch
s
tep
)
:
T
ak
e
ac
tio
n
,
o
b
s
er
v
e
,
′
C
h
o
o
s
e
′
f
r
o
m
′
u
s
in
g
d
er
iv
ed
f
r
o
m
(
,
)
←
(
,
)
+
[
+
(
′
,
′
)
−
(
,
)
]
←
′
←
′
Unt
il
is
ter
m
in
al
(
a)
(
b
)
Fig
u
r
e
1
.
Ps
eu
d
o
c
o
d
e
o
f
R
L
w
ith
T
D
-
p
o
licy
: (
a
)
Q
-
le
ar
n
in
g
p
s
eu
d
o
co
d
e
an
d
(
b
)
SAR
SA p
s
eu
d
o
co
d
e
2
.
3
.
K
no
wledg
e
g
ro
wing
E
n
ter
tain
m
en
t
p
u
r
p
o
s
e
co
n
s
is
ts
o
f
:
mu
s
ik
/p
lay
in
g
m
u
s
ic
a
u
d
io
,
d
o
n
g
en
g
/p
lay
in
g
f
air
y
tale
au
d
io
,
ko
med
i
/p
lay
in
g
co
m
e
d
y
a
u
d
io
.
Mo
tiv
atio
n
p
u
r
p
o
s
e,
c
o
n
s
is
t
o
f
mo
tiva
s
i
/Pl
ay
in
g
m
o
tiv
atio
n
au
d
i
o
.
E
m
er
g
en
c
y
p
u
r
p
o
s
e:
mem
a
n
g
g
il
p
era
w
a
t
/callin
g
n
u
r
s
e,
ke
lu
h
a
n
/r
ep
o
r
ti
n
g
co
m
p
lain
t
o
f
p
ain
.
Help
in
g
p
u
r
p
o
s
e,
tak
i
n
g
an
o
b
ject/p
atien
t’
s
b
elo
n
g
in
g
s
.
R
esear
ch
er
s
h
av
e
em
p
h
asized
o
n
im
p
lem
en
tin
g
r
o
b
o
ts
th
at
ca
n
im
itate
o
wn
in
g
m
em
o
r
y
/k
n
o
wled
g
e
to
m
itig
at
e
m
an
y
s
o
ci
al
-
r
o
b
o
t
ch
allen
g
e
s
[
2
7
]
,
s
o
m
e
s
tu
d
ies
h
av
e
ex
p
lo
it
d
ata,
b
ased
on
u
s
er
p
r
o
f
ile
[
2
8
,
2
9
]
to
m
ak
e
m
em
o
r
y
-
b
ased
ad
ap
tatio
n
s
.
W
e
im
p
lem
en
t
r
o
b
o
t
ask
in
g
d
u
r
in
g
in
ter
ac
tio
n
to
g
ath
er
n
ew
in
f
o
r
m
atio
n
f
r
o
m
h
u
m
an
f
ee
d
b
ac
k
,
Fig
u
r
e
2
(
a
)
is
an
ex
am
p
le
o
f
ad
d
itio
n
al
k
n
o
wled
g
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
3
,
J
u
n
e
2
0
2
1
:
93
1
-
9
38
934
E
n
ter
tain
m
en
t,
m
o
tiv
atio
n
,
an
d
em
er
g
e
n
cy
n
ee
d
b
ac
k
-
en
d
in
ter
v
e
n
tio
n
f
r
o
m
ad
m
in
to
ad
d
ap
p
r
o
p
r
iate
co
n
ten
t
m
a
n
u
ally
.
I
n
em
er
g
e
n
cy
,
th
e
r
o
b
o
t
b
e
h
av
io
r
(
ca
llin
g
n
u
r
s
e
in
f
ix
p
lace
,
wh
er
e
r
o
b
o
t
m
o
v
es,
an
d
wh
at
r
o
b
o
t
talk
)
ca
n
n
o
t
b
e
c
h
an
g
e
d
b
y
u
s
er
/p
a
tien
t
.
Mea
n
wh
ile,
h
elp
in
g
is
m
o
v
in
g
ac
tio
n
f
r
o
m
r
o
b
o
t
th
at
d
e
p
en
d
s
o
n
u
s
e
r
/p
a
tien
t
h
ab
it
o
n
lo
ca
tin
g
h
is
/h
er
b
elo
n
g
in
g
s
,
s
o
it
ca
n
b
e
u
s
ef
u
l
to
u
s
e
en
d
-
u
s
er
ex
p
er
ien
ce
.
O
n
ly
f
o
r
th
is
k
in
d
o
f
ac
tio
n
r
o
b
o
t w
ill g
r
o
w
u
p
its
k
n
o
wled
g
e.
T
h
e
h
elp
in
g
co
n
v
er
s
atio
n
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
(
a)
.
Gr
ey
s
h
ad
es
s
h
o
w
th
e
u
n
k
n
o
wn
o
f
r
o
b
o
t,
th
e
n
f
r
o
m
th
e
co
n
v
er
s
atio
n
s
th
at
w
e
p
r
o
p
o
s
ed
th
en
ap
p
ea
r
wo
r
d
s
in
cy
an
,
y
ello
w,
a
n
d
o
r
a
n
g
e
s
h
ad
es,
th
at
is
n
ew
k
n
o
wled
g
e.
New
k
n
o
wled
g
e
will b
e
s
av
ed
at
Q
-
T
ab
le
s
h
o
w
n
in
Fig
u
r
e
2
(
b
)
f
o
r
f
u
r
th
er
t
r
a
in
in
g
,
th
en
R
L
b
o
th
Q
-
lea
r
n
in
g
a
n
d
SAR
SA ta
k
es
p
ar
t
o
n
b
u
ild
n
ew
en
v
ir
o
n
m
e
n
t b
y
ca
lcu
latin
g
r
ewa
r
d
s
at
ea
c
h
ac
tio
n
an
d
s
tate.
(
a)
(
b
)
Fig
u
r
e
2
.
(
a
)
Ad
d
itio
n
al
k
n
o
wled
g
e
g
ath
e
r
s
f
r
o
m
d
ialo
g
u
e
an
d
(
b
)
New
k
n
o
wled
g
e
s
to
r
ed
i
n
d
atab
ase
2
.
4
.
Na
t
u
ra
l
la
ng
ua
g
e
g
ener
a
t
io
n
Natu
r
al
lan
g
u
ag
e
g
e
n
er
atio
n
(
NL
G)
is
r
esp
o
n
s
ib
le
to
g
en
er
ate
lin
g
u
is
tic
r
ea
lizatio
n
o
f
th
e
s
y
s
tem
'
s
d
ialo
g
u
e.
T
h
e
g
o
al
o
f
NL
G
is
to
p
r
o
d
u
ce
s
p
o
k
en
th
at
is
ea
s
y
f
o
r
h
u
m
a
n
s
to
u
n
d
er
s
tan
d
.
I
n
th
is
p
ap
er
we
h
ad
3
r
esp
o
n
s
e
s
y
s
tem
s
th
er
e
ar
e
r
ejec
tio
n
,
ask
in
g
,
a
n
d
a
b
o
r
tin
g
.
On
ce
s
y
s
tem
f
o
u
n
d
th
at
all
wo
r
d
in
a
s
en
te
n
ce
h
as
n
o
v
e
r
b
(
lis
ted
o
n
co
r
p
u
s
)
o
r
u
n
iq
u
e
wo
r
d
s
,
s
y
s
tem
w
ill
r
ejec
t
an
d
r
eq
u
est
to
ch
an
g
e
with
o
th
er
n
ew
wo
r
d
s
u
n
til
th
e
r
e
is
v
er
b
o
r
u
n
iq
u
e
wo
r
d
in
th
at
s
en
ten
ce
.
Ask
in
g
r
e
s
p
o
n
s
e
is
s
tar
ted
wit
h
s
ea
r
ch
in
g
v
er
b
in
s
y
s
tem
d
atab
ase
k
n
o
wled
g
e,
i
f
th
er
e
is
n
o
s
im
ilar
v
er
b
th
e
n
s
y
s
tem
will
ca
teg
o
r
ize
it
as
n
ew
v
er
b
with
n
o
r
elatio
n
to
o
b
ject.
T
h
e
s
y
s
tem
will
ask
f
o
r
o
b
ject
t
h
en
s
ea
r
c
h
in
g
t
h
e
wo
r
d
i
n
c
o
r
p
u
s
,
i
f
t
h
er
e
is
o
b
ject
in
t
h
e
co
r
p
u
s
th
en
s
y
s
tem
will
s
ea
r
ch
in
d
atab
ase.
T
h
at
is
wh
y
s
o
m
e
v
er
b
s
ca
n
h
a
v
e
o
n
e
s
am
e
o
b
ject.
Af
ter
t
h
e
s
y
s
tem
h
as
n
ew
v
er
b
a
n
d
n
e
w
o
b
ject,
th
en
s
y
s
tem
will
as
k
f
o
r
p
lace
,
if
s
y
s
tem
a
b
le
to
f
u
lf
ill
d
ir
ec
tio
n
a
n
d
iter
atio
n
,
th
e
n
it
will
s
av
e
as
n
ew
k
n
o
wle
d
g
e
.
Ab
o
r
tin
g
r
esp
o
n
s
e
is
wh
er
e
t
h
e
s
y
s
tem
will
ab
le
to
ab
o
r
t
m
is
s
io
n
if
u
s
er
s
ay
s
teri
ma
ka
s
ih
/th
an
k
y
o
u
in
th
e
m
id
d
le
o
f
ask
in
g
co
n
v
er
s
atio
n
.
2
.
5
.
H
u
m
a
no
id
ro
bo
t
B
io
lo
id
g
r
an
d
p
r
ix
(
GP)
is
a
h
u
m
an
o
id
r
o
b
o
t
e
q
u
ip
p
ed
with
C
M
-
5
3
0
co
n
tr
o
ller
,
an
d
lith
iu
m
b
atter
y
f
o
r
p
o
wer
s
u
p
p
ly
[
3
0
]
.
W
e
u
s
e
m
o
d
if
ied
B
io
lo
id
GP
f
r
o
m
[
1
3
]
as
p
r
ev
io
u
s
p
r
o
ject
with
a
n
ad
d
itio
n
al
s
p
ea
k
er
m
o
u
n
ted
o
n
to
p
o
f
th
e
r
o
b
o
t.
An
alo
g
v
o
ltag
es
f
r
o
m
A
r
d
u
in
o
Me
g
a
2
5
6
0
[
3
1
]
ar
e
co
n
v
er
t
ed
to
d
ig
ital
v
al
u
es
by
an
alo
g
to
d
i
g
ital
co
n
v
er
ter
(
ADC)
as
a
r
ef
er
en
ce
co
m
m
an
d
f
o
r
C
M
-
5
3
0
th
at
will
b
e
t
r
an
s
lated
in
to
r
o
b
o
t
m
o
v
em
en
t
.
R
o
b
o
t m
o
v
em
en
t
co
n
s
is
ts
o
f
f
o
r
war
d
,
b
ac
k
war
d
,
lef
t,
an
d
r
ig
h
t w
ith
its
iter
atio
n
.
2
.
6
.
Sy
s
t
e
m
im
plem
ent
a
t
io
n
T
h
e
h
ar
d
war
e
n
ee
d
ed
f
o
r
th
is
s
y
s
tem
is
a
m
icr
o
p
h
o
n
e
i
n
p
u
t
(
Kin
ec
t
2
.
0
)
,
p
r
o
ce
s
s
o
r
(
L
ap
to
p
)
,
co
n
tr
o
ller
(
Ar
d
u
in
o
a
n
d
C
M
-
5
3
0
)
,
an
d
o
u
tp
u
t
in
th
e
f
o
r
m
o
f
s
p
ea
k
er
s
an
d
r
o
b
o
ts
as
s
h
o
wn
in
Fig
u
r
e
3
(
a)
.
I
n
th
e
h
ar
d
war
e
im
p
lem
en
tatio
n
,
r
o
b
o
t a
b
le
to
m
o
v
e
ev
er
y
wh
er
e
with
o
u
t w
ir
e
o
n
ca
b
le
as sh
o
wn
in
Fig
u
r
e
3
(
b
)
.
Sp
ee
ch
o
u
t
p
u
t
a
n
d
r
o
b
o
t
m
o
v
em
en
t
co
n
tr
o
l
a
r
e
s
en
t
f
r
o
m
l
ap
to
p
t
o
Ar
d
u
in
o
v
ia
b
lu
eto
o
t
h
.
W
e
u
s
ed
Go
o
g
le
s
p
ee
ch
r
ec
o
g
n
itio
n
with
id
-
I
D
(
I
n
d
o
n
esian
lan
g
u
ag
e
)
to
r
ec
o
g
n
ize
an
d
ad
j
u
s
t
am
b
ien
t
n
o
i
s
e.
L
ap
to
p
p
o
wer
ed
b
y
th
e
I
n
tel
C
o
r
e
i5
p
r
o
ce
s
s
o
r
,
8
GB
o
f
m
em
o
r
y
.
W
e
u
s
e
p
y
t
h
o
n
lan
g
u
ag
e
an
d
R
L
alg
o
r
ith
m
b
u
ild
s
o
n
it.
W
e
eq
u
ip
p
e
d
r
o
b
o
t
v
o
ice
with
s
p
ee
ch
r
eg
is
tr
y
f
r
o
m
W
in
d
o
ws
ca
lled
Mic
r
o
s
o
f
t
An
d
ik
a
to
g
i
v
e
I
n
d
o
n
esian
v
o
ice
an
d
ac
ce
n
t
,
also
p
r
o
n
o
u
n
ce
ca
r
d
in
al
n
u
m
b
er
in
I
n
d
o
n
esian
.
W
e
s
et
r
o
b
o
t
to
talk
1
5
0
w
o
r
d
s
p
er
m
in
u
te
(
W
PM)
.
Th
e
av
er
ag
e
s
p
ee
c
h
r
ate
f
o
r
co
n
v
er
s
atio
n
al
is
1
2
0
-
1
5
0
W
PM
[
3
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dia
lo
g
u
e
ma
n
a
g
eme
n
t
u
s
in
g
r
ein
fo
r
ce
men
t le
a
r
n
in
g
(
B
in
a
s
h
ir
R
o
fi’a
h
)
935
(
a)
(
b
)
Fig
u
r
e
3
.
Sy
s
tem
c
o
n
f
ig
u
r
atio
n
: (
a)
d
esig
n
,
an
d
(
b
)
im
p
lem
e
n
tatio
n
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
W
e
co
n
d
u
cted
s
ev
er
al
e
x
p
er
i
m
en
ts
t
o
s
ee
th
e
p
er
f
o
r
m
an
c
e
o
f
s
y
s
tem
.
Sy
s
tem
co
n
f
i
g
u
r
atio
n
an
d
en
v
ir
o
n
m
en
t
as
s
h
o
wn
in
Fi
g
u
r
e
3
(
b
)
.
T
h
e
p
er
f
o
r
m
an
ce
will
r
ep
r
esen
t
h
o
w
f
ast
r
o
b
o
t
ex
ec
u
tio
n
,
h
o
w
ac
cu
r
ate,
an
d
h
o
w
k
n
o
wled
g
e
g
r
o
win
g
.
T
h
e
ex
p
e
r
im
en
t
co
n
s
is
ts
o
f
en
ter
tain
m
en
t
ex
ec
u
tio
n
,
em
er
g
en
cy
ex
ec
u
tio
n
,
h
elp
in
g
co
n
v
er
s
atio
n
with
k
n
o
wled
g
e
g
r
o
win
g
,
p
o
li
cy
b
eh
av
io
r
,
an
d
r
ewa
r
d
co
n
v
er
g
en
ce
.
3
.
1
.
E
nte
rt
a
inm
ent
e
x
ec
utio
n
T
h
is
ex
p
er
im
en
t
g
iv
e
d
u
s
in
s
ig
h
t
o
n
ex
ec
u
tio
n
tim
e
f
o
r
s
in
g
le
r
eq
u
est.
W
e
im
p
lem
en
te
d
u
s
in
g
1
m
f
ix
ed
d
is
tan
ce
.
T
im
e
co
u
n
ted
r
ig
h
t
af
ter
tr
an
s
latio
n
f
r
o
m
s
p
ee
ch
to
tex
t
,
w
e
d
id
it
b
ec
au
s
e
th
e
len
g
th
o
f
d
ialo
g
u
es
an
d
t
h
e
s
p
ee
d
o
f
p
eo
p
le’
s
s
p
ee
ch
r
ates
v
ar
ie
d
.
An
av
er
a
g
e
tim
e
wa
s
3
.
7
4
m
s
.
T
h
e
s
lo
west
tim
e
o
cc
u
r
s
o
n
p
u
r
p
le
s
h
ad
e
with
8
.
2
3
m
s
.
T
h
e
f
astes
t tim
e
was 0
.
8
6
m
s
with
p
in
k
s
h
ad
e
s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
T
im
e
f
o
r
e
n
ter
tain
m
e
n
t e
x
ec
u
tio
n
D
i
a
l
o
g
u
e
Mu
s
i
k
/
M
u
si
c
D
o
n
g
e
n
g
/
F
a
i
r
y
t
a
l
e
Mo
t
i
v
a
s
i
/
M
o
t
i
v
a
t
i
o
n
K
o
m
e
d
i
/
C
o
m
e
d
y
[
r
e
q
u
e
st
]
2
.
9
9
2
.
0
0
3
.
9
2
3
.
9
1
n
y
a
l
a
k
a
n
l
a
h
[re
q
u
e
s
t
]
(
p
l
e
a
se
t
u
r
n
o
n
[
r
e
q
u
e
st
]
)
5
.
7
6
1
.
9
9
5
.
1
8
3
.
6
0
m
a
i
n
k
a
n
l
a
h
[re
q
u
e
st
]
(
p
l
e
a
se
p
l
a
y
[
r
e
q
u
e
st
]
)
2
.
0
0
2
.
0
1
5
.
3
4
4
.
1
6
m
a
i
n
k
a
n
[re
q
u
e
s
t
]n
y
a
(
p
l
a
y
t
h
e
[
r
e
q
u
e
st
]
)
2
.
0
1
2
.
0
0
2
.
7
9
0
.
8
6
sa
y
a
i
n
g
i
n
m
e
n
d
e
n
g
a
r
k
a
n
[re
q
u
e
st
]
(
I
w
a
n
t
t
o
l
i
s
t
e
n
t
o
[
r
e
q
u
e
s
t
]
)
2
.
0
0
1
.
0
3
7
.
4
7
4
.
9
0
[req
u
e
s
t
]
y
a
n
g
b
a
g
u
s
(
p
l
e
a
se
t
h
e
b
e
st
[
r
e
q
u
e
s
t
]
)
8
.
2
3
2
.
0
0
6
.
3
5
6
.
8
1
sa
y
a
b
o
sa
n
i
n
g
i
n
[
re
q
u
e
st
]
(
I
a
m b
o
r
e
d
,
w
a
n
t
t
o
[
r
e
q
u
e
st
]
)
2
.
5
5
2
.
0
3
1
.
9
9
5
.
8
5
sa
y
a
b
u
t
u
h
[re
q
u
e
st
]
(
I
n
e
e
d
[
r
e
q
u
e
s
t
]
)
3
.
9
1
2
.
0
0
7
.
1
0
3
.
9
1
[req
u
e
s
t
]
n
y
a
,
t
o
l
o
n
g
d
i
p
u
t
a
r
(
t
h
e
[
r
e
q
u
e
s
t
]
,
p
l
e
a
s
e
p
l
a
y
)
2
.
0
0
2
.
0
3
3
.
9
9
6
.
6
0
m
i
n
t
a
t
o
l
o
n
g
[
re
q
u
e
st
]
(
p
l
e
a
se
[
r
e
q
u
e
s
t
]
)
7
.
4
8
1
.
0
3
3
.
3
6
4
.
3
1
A
v
e
r
a
g
e
t
i
me
l
e
v
e
l
3
.
7
4
3
.
2
.
E
m
er
g
ency
ex
ec
utio
n
I
n
em
er
g
e
n
cy
s
itu
atio
n
,
we
ask
ed
r
o
b
o
t
to
ca
ll
n
u
r
s
e
b
y
talk
u
n
iq
u
e
wo
r
d
“
p
era
w
a
t
(
n
u
r
s
e)
”.
W
e
u
s
e
s
en
ten
ce
“p
a
n
g
g
ilka
n
p
era
w
a
t
(
ca
ll th
e
n
u
r
s
e)
”,
th
en
r
o
b
o
t w
ill ask
f
o
r
co
m
p
lain
t o
f
p
ain
.
Af
ter
co
n
v
er
s
atio
n
,
r
o
b
o
t
will
walk
to
t
h
e
p
lace
w
h
er
e
th
e
n
u
r
s
e
u
s
u
ally
s
tan
d
b
y
an
d
d
escr
ib
e
co
m
p
lai
n
t
o
f
p
ai
n
to
th
e
n
u
r
s
e.
On
th
e
o
th
er
h
an
d
,
th
e
co
m
p
lain
t
will r
ec
o
r
d
o
n
a
r
ep
o
r
t sh
o
wn
i
n
T
ab
le
2
.
3
.
3
.
K
no
wledg
e
g
ro
wing
I
n
b
e
g
in
n
in
g
t
h
er
e
w
er
e
o
n
l
y
2
v
er
b
s
an
d
2
o
b
jects,
th
e
n
d
u
r
in
g
th
is
ex
p
er
im
en
t,
h
u
m
an
g
i
v
es
u
n
k
n
o
wn
k
n
o
wled
g
e
to
r
o
b
o
t.
Fro
m
th
e
co
n
v
er
s
atio
n
s
,
k
n
o
wled
g
e
ex
p
a
n
d
ed
to
1
0
v
er
b
s
an
d
8
o
b
jects.
W
e
also
tr
ied
d
if
f
er
en
t
v
er
b
s
r
elat
ed
to
s
am
e
o
b
ject.
To
n
t
o
n
/wa
tch
an
d
lih
a
t
/s
ee
h
av
e
th
e
s
a
m
e
o
b
ject
th
at
was
r
em
o
te.
Tu
lis
/
wr
ite
an
d
ca
ta
t
/r
ec
o
r
d
h
a
v
e
s
am
e
o
b
ject
,
th
at
wa
s
p
en
cil.
W
e
s
ep
ar
ate
d
Q
-
T
ab
le
f
o
r
Q
-
lear
n
in
g
a
n
d
SAR
SA
b
ec
au
s
e
th
e
r
ewa
r
d
s
ar
e
d
if
f
er
en
t.
Q
-
le
ar
n
in
g
r
ewa
r
d
is
s
h
o
wn
i
n
T
ab
le
3
,
t
h
e
b
lu
e
s
h
ad
es
m
ea
n
th
e
h
i
g
h
est
r
ewa
r
d
th
at
was
co
n
n
ec
ted
b
etwe
en
v
e
r
b
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
3
,
J
u
n
e
2
0
2
1
:
93
1
-
9
38
936
ob
ject
o
n
th
e
Q
-
t
ab
le
.
W
h
er
ea
s
T
ab
le
4
was
th
e
f
in
al
SA
R
SA
Q
-
T
ab
le
wh
ich
h
as
m
o
r
e
n
u
ll/zer
o
v
alu
es.
I
n
SAR
S
A
p
o
licy
,
wh
e
n
s
tate
is
ter
m
in
al
th
en
r
ewa
r
d
will
b
e
g
r
o
u
n
d
ed
to
ze
r
o
.
T
h
e
h
ig
h
est
r
ewa
r
d
s
ar
e
s
h
o
wn
in
o
r
an
g
e
s
h
ad
es.
W
e
also
d
id
an
ex
p
er
i
m
en
t
to
ex
e
c
u
te
tr
ai
n
in
g
f
r
o
m
1
k
n
o
wled
g
e
to
1
0
k
n
o
wled
g
e
i
n
2
0
0
ep
is
o
d
es.
E
v
er
y
ex
ec
u
tio
n
iter
ates
3
tim
es
f
o
r
Q
-
lea
r
n
in
g
an
d
SAR
S
A.
Fro
m
k
n
o
wled
g
e
1
u
n
til
5
,
tim
e
was
v
ar
y
in
g
,
h
o
wev
er
f
r
o
m
6
k
n
o
wled
g
e
,
tim
e
co
n
s
is
ten
tly
r
am
p
u
p
f
r
o
m
1
4
0
5
u
n
til
3
49
0
m
s
,
an
d
Q
-
lea
r
n
i
n
g
n
ee
d
s
m
o
r
e
tim
e
t
h
an
SAR
SA
as sh
o
wn
i
n
Fig
u
r
e
4
.
T
ab
le
2
.
R
ep
o
r
t
o
f
em
e
r
g
en
c
y
/co
m
p
lain
t
o
f
Pain
D
a
t
e
Ti
m
e
C
o
m
p
l
a
i
n
t
o
f
P
a
i
n
8
/
1
1
/
2
0
2
0
2
2
:
4
4
sa
y
a
p
u
si
n
g
m
u
a
l
(
I
f
e
e
l
d
i
z
z
y
a
n
d
n
a
u
se
a
)
8
/
1
2
/
2
0
2
0
1
6
:
2
1
sa
y
a
n
y
e
ri
(
I
a
m
i
n
p
a
i
n
)
8
/
1
2
/
2
0
2
0
1
6
:
2
1
i
n
f
u
s
s
a
y
a
l
e
p
a
s
(
M
y
i
n
f
u
si
o
n
p
e
e
l
s
o
f
f
)
8
/
1
2
/
2
0
2
0
1
6
:
2
2
sa
y
a
b
a
t
u
k
d
a
ra
h
(
I
c
o
u
g
h
e
d
u
p
b
l
o
o
d
)
8
/
1
2
/
2
0
2
0
1
6
:
3
2
sa
y
a
s
e
sa
k
n
a
f
a
s
(
I
a
m sh
o
r
t
o
f
b
r
e
a
t
h
)
8
/
1
2
/
2
0
2
0
1
6
:
3
3
sa
y
a
m
e
r
i
a
n
g
(
I
f
e
e
l
l
i
g
h
t
-
h
e
a
d
e
d
)
8
/
1
2
/
2
0
2
0
1
6
:
3
3
sa
y
a
s
a
k
i
t
p
e
ru
t
t
i
b
a
t
i
b
a
(
I
h
a
v
e
a
su
d
d
e
n
s
t
o
m
a
c
h
a
c
h
e
)
T
ab
le
3
.
Q
-
T
a
b
le
f
o
r
Q
-
L
ea
r
n
i
n
g
W
a
l
l
e
t
P
e
n
c
i
l
B
l
a
n
k
e
t
P
u
z
z
l
e
R
e
m
o
t
e
B
o
o
k
B
a
r
b
e
l
l
Ti
ss
u
e
L
R
L
R
L
R
L
R
L
R
L
R
L
R
L
R
S
a
v
e
N
o
n
e
1
0
0
99
80
89
72
80
65
72
59
65
53
59
47
53
N
o
n
e
W
r
i
t
e
N
o
n
e
92
1
0
0
1
0
0
99
80
89
72
80
65
72
59
65
53
59
N
o
n
e
N
o
t
e
N
o
n
e
89
1
0
0
1
0
0
99
80
89
72
80
65
72
59
65
53
59
N
o
n
e
S
l
e
e
p
N
o
n
e
88
73
99
1
0
0
1
0
0
99
80
89
72
80
65
72
59
65
N
o
n
e
P
l
a
y
N
o
n
e
80
72
89
80
99
1
0
0
1
0
0
99
80
89
72
80
65
72
N
o
n
e
W
a
t
c
h
N
o
n
e
72
65
80
72
89
80
99
1
0
0
1
0
0
99
80
89
72
80
N
o
n
e
R
e
a
d
No
ne
65
59
72
65
80
72
89
80
99
1
0
0
1
0
0
99
64
85
N
o
n
e
S
e
e
N
o
n
e
72
65
80
72
89
80
99
1
0
0
1
0
0
99
79
89
71
80
N
o
n
e
Ex
e
r
c
i
se
N
o
n
e
59
53
65
59
72
66
81
73
89
80
99
1
0
0
1
0
0
96
N
o
n
e
C
l
e
a
n
N
o
n
e
53
47
59
53
65
59
72
65
80
72
89
80
99
1
0
0
N
o
n
e
T
ab
le
4
.
Q
-
T
a
b
le
f
o
r
SAR
SA
W
a
l
l
e
t
P
e
n
c
i
l
B
l
a
n
k
e
t
P
u
z
z
l
e
R
e
m
o
t
e
B
o
o
k
B
a
r
b
e
l
l
Ti
ss
u
e
L
R
L
R
L
R
L
R
L
R
L
R
L
R
L
R
S
a
v
e
N
o
n
e
1
0
0
99
0
89
0
80
0
72
0
65
0
59
0
53
N
o
n
e
W
r
i
t
e
N
o
n
e
93
1
0
0
1
0
0
99
0
89
0
80
0
72
0
65
0
59
N
o
n
e
N
o
t
e
N
o
n
e
91
1
0
0
1
0
0
99
0
89
0
80
0
72
0
65
0
59
N
o
n
e
S
l
e
e
p
N
o
n
e
85
0
98
1
0
0
1
0
0
99
0
89
0
80
0
72
0
65
N
o
n
e
P
l
a
y
N
o
n
e
80
0
89
0
99
1
0
0
1
0
0
99
0
89
0
80
0
72
N
o
n
e
W
a
t
c
h
N
o
n
e
72
0
80
0
89
0
99
1
0
0
1
0
0
99
0
89
0
80
N
o
n
e
R
e
a
d
N
o
n
e
65
0
72
0
80
0
89
0
99
1
0
0
1
0
0
99
0
88
N
o
n
e
S
e
e
N
o
n
e
72
0
80
0
89
0
9
9
1
0
0
1
0
0
99
0
89
0
80
N
o
n
e
Ex
e
r
c
i
se
N
o
n
e
59
0
65
0
72
0
80
0
89
0
99
1
0
0
1
0
0
81
N
o
n
e
C
l
e
a
n
N
o
n
e
53
0
59
0
65
0
72
0
80
0
89
0
99
1
0
0
N
o
n
e
Fig
u
r
e
4
.
E
x
ec
u
tio
n
t
im
e
as
k
n
o
wled
g
e
in
cr
ea
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
Dia
lo
g
u
e
ma
n
a
g
eme
n
t
u
s
in
g
r
ein
fo
r
ce
men
t le
a
r
n
in
g
(
B
in
a
s
h
ir
R
o
fi’a
h
)
937
3
.
4
.
P
o
licy
beha
v
io
r
T
o
k
n
o
w
th
e
m
o
v
em
en
t
o
f
p
o
licy
an
d
ac
ti
o
n
s
tak
en
in
a
ce
r
t
ain
s
tate
to
r
ea
ch
ap
p
r
o
p
r
iate
o
b
ject,
we
also
tak
in
g
p
l
o
t
s
f
o
r
r
ewa
r
d
v
alu
e
at
th
e
en
d
o
f
ep
is
o
d
e
(
2
0
0
th
ep
is
o
d
e)
.
As
s
h
o
wn
i
n
Fig
u
r
e
5
r
ewa
r
d
s
h
if
t
to
war
d
s
r
emo
t
/
r
em
o
te
in
th
e
m
id
d
le
.
R
ed
s
h
ad
e
m
ea
n
s
th
e
lo
west
r
ewa
r
d
,
wh
er
e
g
r
ee
n
s
h
ad
e
is
th
e
h
ig
h
est
r
ewa
r
d
(
g
o
al)
.
T
h
e
y
ello
w
s
h
a
d
es
d
escr
ib
e
th
e
tr
an
s
itio
n
o
f
r
ewa
r
d
v
alu
e
f
r
o
m
t
h
e
lo
west to
th
e
h
ig
h
est.
Fig
u
r
e
5
.
L
e
f
t a
n
d
r
ig
h
t
p
o
licy
d
ir
ec
tio
n
to
o
b
ject
“
r
emo
t
/r
e
m
o
t
e
”
3
.
5
.
Rew
a
rd
co
nv
er
g
ence
On
th
is
im
p
lem
en
tatio
n
,
we
wan
t
to
k
n
o
w
th
e
p
e
r
f
o
r
m
an
ce
o
f
Q
-
lear
n
in
g
an
d
SAR
SA
f
o
r
ev
er
y
o
b
ject
in
ea
ch
f
i
n
al
r
ewa
r
d
f
o
r
2
0
0
ep
is
o
d
es.
Star
t
f
r
o
m
1
to
7
o
b
jects.
I
t
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
6
t
h
at
th
e
SAR
S
A
cu
m
u
lativ
e
r
ewa
r
d
w
as
s
lig
h
tly
h
ig
h
er
th
an
Q
-
L
ea
r
n
in
g
,
wh
ich
m
ea
n
s
th
at
its
al
g
o
r
ith
m
was
f
aster
to
war
d
s
s
tead
y
s
tates
b
ec
au
s
e
SAR
S
A
'
s
p
o
licy
d
o
es
n
o
t
ex
p
lo
r
e
all
ac
tio
n
s
at
ea
ch
s
tep
s
o
th
at
it
was
f
o
cu
s
ed
to
g
et
th
e
g
o
al.
Fig
u
r
e
6
.
C
u
m
u
lativ
e
r
ewa
r
d
b
etwe
en
Q
-
l
ea
r
n
in
g
an
d
SAR
SA
4.
CO
NCLU
SI
O
N
Fro
m
th
e
e
x
p
er
im
e
n
t
in
p
r
ev
i
o
u
s
s
ec
tio
n
,
it
co
u
ld
b
e
s
h
o
wn
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
tem
h
as
th
e
ab
ilit
y
to
ex
p
a
n
d
f
r
o
m
2
to
10
k
n
o
wl
ed
g
e.
A
d
d
itio
n
al
k
n
o
wled
g
e
a
f
f
ec
ted
to
th
e
tim
e
f
o
r
lear
n
in
g
ex
ec
u
tio
n
th
at
was
g
ettin
g
lo
n
g
er
f
r
o
m
1
4
0
5
m
s
to
3
49
0
m
s
.
SAR
SA
wa
s
f
aster
to
war
d
s
s
tead
y
s
tate
b
ec
au
s
e
o
f
h
i
g
h
er
cu
m
u
lativ
e
r
ewa
r
d
s
.
H
o
wev
er
,
th
e
d
if
f
er
en
ce
b
etwe
en
o
f
f
a
n
d
o
n
lear
n
i
n
g
ca
n
s
till
b
e
im
p
lem
en
ted
,
an
d
th
e
p
o
licy
m
o
v
es
th
e
ac
tio
n
ac
co
r
d
in
g
l
y
to
ac
h
iev
e
th
e
d
e
s
ir
ed
o
b
ject
i
n
2
0
0
ep
is
o
d
e
s
.
E
q
u
ip
p
ed
with
en
ter
tain
m
en
t f
ea
tu
r
e
t
o
p
la
y
m
u
s
ic,
f
air
y
tale,
m
o
tiv
atio
n
,
a
n
d
co
m
ed
y
r
eq
u
est
in
f
ast
av
e
r
ag
e
ex
ec
u
tio
n
tim
e
o
f
3
.
7
4
m
s
.
Du
r
in
g
em
er
g
e
n
c
y
s
itu
atio
n
s
y
s
tem
ab
le
to
ca
ll
n
u
r
s
e
an
d
s
av
e
7
co
m
p
lain
ts
o
f
p
ain
.
I
t
co
u
ld
b
e
co
n
clu
d
e
d
th
at
th
e
m
eth
o
d
p
r
o
p
o
s
ed
i
n
th
is
p
ap
e
r
s
u
cc
ess
f
u
lly
ac
h
iev
e
d
th
e
o
b
jectiv
e
t
o
o
v
er
c
o
m
e
r
o
b
o
t
k
n
o
wled
g
e
lim
itatio
n
in
ac
h
i
ev
in
g
n
ew
d
ialo
g
u
e
g
o
al
f
o
r
p
atien
t
ass
i
s
tan
t
.
Fo
r
f
u
r
th
er
r
esear
ch
,
d
ialo
g
u
e
class
if
icatio
n
an
d
k
n
o
wled
g
e
g
r
o
win
g
ca
n
b
e
e
x
ten
d
e
d
f
o
r
c
h
it
-
ch
at
d
ialo
g
u
e
o
r
n
o
n
-
g
o
al
d
r
iv
en
.
RE
F
E
R
E
NC
E
S
[1
]
C.
F
.
S
a
n
to
s
,
“
Re
flec
ti
o
n
s
a
b
o
u
t
th
e
imp
a
c
t
o
f
t
h
e
S
ARS
-
COV
-
2
/COVID
-
1
9
p
a
n
d
e
m
ic
o
n
m
e
n
t
a
l
h
e
a
lt
h
,
”
Rev
.
Bra
s.
Psiq
u
i
a
tr.
,
v
o
l
.
4
2
,
n
o
.
3
,
p
.
3
2
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
5
9
0
/
1
5
1
6
-
4
4
4
6
-
2
0
2
0
-
0
9
8
1
.
[2
]
D.
M
.
M
o
re
n
s,
G
.
K.
F
o
l
k
e
rs,
a
n
d
A.
S
.
F
a
u
c
i,
“
W
h
a
t
Is
a
P
a
n
d
e
m
ic?
,
”
J
.
In
fec
t.
Dis.
,
v
o
l.
2
0
0
,
n
o
.
7
,
p
p
.
1
0
1
8
-
1
0
2
1
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
8
6
/6
4
4
5
3
7
.
[3
]
Ce
n
ter
fo
r
th
e
S
tu
d
y
o
f
Trau
m
a
ti
c
S
tres
s,
“
P
sy
c
h
o
lo
g
ica
l
Eff
e
c
ts
o
f
Qu
a
ra
n
ti
n
e
Du
ri
n
g
t
h
e
Co
ro
n
a
v
iru
s
Ou
t
b
re
a
k
:
Wh
a
t
He
a
lt
h
c
a
re
P
ro
v
id
e
rs Ne
e
d
to
Kn
o
w,” p
p
.
1
-
2
,
2
0
2
0
.
l
e
ft
r
i
g
h
t
l
e
ft
r
i
g
h
t
l
e
ft
r
i
g
h
t
l
e
ft
r
i
g
h
t
l
e
f
t
r
i
g
ht
l
e
ft
r
i
g
h
t
l
e
ft
r
i
g
h
t
l
e
ft
r
i
g
h
t
Q
-
L
e
a
r
n
i
n
g
0
.
0
0
7
2
.
8
9
6
5
.
5
9
8
0
.
9
9
7
2
.
8
8
9
0
.
0
0
8
0
.
9
4
9
9
.
9
9
1
0
0
.0
0
1
0
0
.0
0
9
9
.
9
1
7
9
.
4
0
8
9
.
7
3
7
1
.
1
1
8
0
.
2
2
0
.
0
0
S
A
R
S
A
0
.
0
0
7
2
.
8
6
0
.
0
0
8
0
.
9
8
0
.
0
0
8
9
.
9
9
8
0
.
9
4
9
9
.
9
9
1
0
0
.0
0
1
0
0
.0
0
9
9
.
9
7
0
.
0
0
8
9
.
9
4
0
.
0
0
8
0
.
8
7
0
.
0
0
l
e
f
t
l
e
f
t
r
i
g
h
t
r
i
g
h
t
r
i
g
h
t
r
i
g
h
t
d
o
n
e
l
e
f
t
B
a
r
b
e
l
l
s
T
i
s
s
u
e
D
o
m
p
e
t
P
e
n
s
i
l
Se
l
i
m
u
t
P
u
z
z
l
e
R
e
m
o
t
B
u
k
u
B
a
r
b
e
l
T
i
s
u
W
a
l
l
e
t
P
e
n
c
i
l
B
l
a
n
k
e
t
P
u
zz
l
e
R
e
m
o
t
e
B
oo
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
3
,
J
u
n
e
2
0
2
1
:
93
1
-
9
38
938
[4
]
M
.
G
o
m
b
o
lay
e
t
a
l.
,
“
Ro
b
o
ti
c
a
ss
istan
c
e
in
c
o
o
rd
i
n
a
ti
o
n
o
f
p
a
ti
e
n
t
c
a
re
,
”
Ro
b
o
t.
S
c
i.
S
y
st.
,
v
o
l.
1
2
,
2
0
1
6
.
[5
]
M
.
Law
e
t
a
l.
,
“
De
v
e
lo
p
i
n
g
a
ss
isti
v
e
ro
b
o
ts
f
o
r
p
e
o
p
le
with
m
i
ld
c
o
g
n
it
i
v
e
imp
a
irme
n
t
a
n
d
m
il
d
d
e
m
e
n
ti
a
:
A
q
u
a
li
tat
i
v
e
stu
d
y
wi
th
o
ld
e
r
a
d
u
lt
s
a
n
d
e
x
p
e
rts
i
n
a
g
e
d
c
a
re
,
”
BM
J
Op
e
n
,
v
o
l.
9
,
n
o
.
9
,
2
0
1
9
.
[6
]
J.
P
e
lt
a
so
n
a
n
d
B.
Wr
e
d
e
,
“
M
o
d
e
li
n
g
h
u
m
a
n
-
r
o
b
o
t
i
n
tera
c
ti
o
n
b
a
se
d
o
n
g
e
n
e
ric
i
n
tera
c
ti
o
n
p
a
tt
e
r
n
s,”
AA
AI
F
a
ll
S
y
mp
.
-
T
e
c
h
.
Rep
.
,
v
o
l
.
F
S
-
10
-
0
5
,
p
p
.
8
0
-
8
5
,
2
0
1
0
.
[7
]
W.
B.
Kn
o
x
a
n
d
P
.
S
to
n
e
,
“
Re
in
fo
rc
e
m
e
n
t
lea
rn
in
g
fr
o
m
sim
u
lt
a
n
e
o
u
s
h
u
m
a
n
a
n
d
M
DP
re
wa
rd
,
”
1
1
t
h
In
t
.
Co
n
f.
Au
to
n
.
Ag
e
n
ts
M
u
lt
ia
g
e
n
t
S
y
st.
2
0
1
2
,
AA
M
AS
2
0
1
2
In
n
o
v
.
A
p
p
l.
T
r
a
c
k
,
v
o
l.
1
,
p
p
.
5
2
8
-
5
3
5
,
2
0
1
2
.
[8
]
K.
Ju
d
a
h
,
S
.
R
o
y
,
A.
F
e
rn
,
a
n
d
T.
G
.
Die
tt
e
rich
,
“
R
e
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
v
ia
p
ra
c
ti
c
e
a
n
d
c
ri
ti
q
u
e
a
d
v
ice
,
”
Pro
c
.
Na
tl
.
C
o
n
f
.
Arti
f
.
In
tell.
,
v
o
l
.
1
,
p
p
.
4
8
1
–
4
8
6
,
2
0
1
0
.
[9
]
K.
P
re
p
i
n
a
n
d
A.
Re
v
e
l,
“
Hu
m
a
n
-
m
a
c
h
in
e
in
tera
c
ti
o
n
a
s
a
m
o
d
e
l
o
f
m
a
c
h
i
n
e
-
m
a
c
h
in
e
in
tera
c
ti
o
n
:
Ho
w
t
o
m
a
k
e
m
a
c
h
in
e
s in
tera
c
t
a
s h
u
m
a
n
s
d
o
,
”
Ad
v
.
R
o
b
o
t.
,
v
o
l.
2
1
,
n
o
.
1
5
,
p
p
.
1
7
0
9
-
1
7
2
3
,
2
0
0
7
.
[1
0
]
D.
Ha
n
d
a
y
a
,
H.
F
a
k
h
r
u
ro
ja,
E.
M
.
I.
Hid
a
y
a
t,
a
n
d
C.
M
a
c
h
b
u
b
,
“
Co
m
p
a
riso
n
o
f
In
d
o
n
e
sia
n
sp
e
a
k
e
r
re
c
o
g
n
i
ti
o
n
u
sin
g
v
e
c
to
r
q
u
a
n
ti
z
a
ti
o
n
a
n
d
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
l
fo
r
u
n
c
lea
r
p
r
o
n
u
n
c
iatio
n
p
ro
b
lem
,
”
Pr
o
c
.
2
0
1
6
6
t
h
I
n
t.
C
o
n
f.
S
y
st.
En
g
.
T
e
c
h
n
o
l.
IC
S
ET
2
0
1
6
,
p
p
.
3
9
-
4
5
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/
F
I
T.
2
0
1
6
.
7
8
5
7
5
3
5
.
[1
1
]
Riy
a
n
to
,
W.
A
d
ip
ra
wita,
H.
Hi
n
d
e
rsa
h
,
a
n
d
C.
M
a
c
h
b
u
b
,
“
Ce
n
ter
o
f
M
a
ss
b
a
se
d
Walk
i
n
g
P
a
tt
e
rn
G
e
n
e
ra
to
r
with
G
ra
v
it
y
Co
m
p
e
n
sa
ti
o
n
fo
r
Wal
k
i
n
g
Co
n
tr
o
l
o
n
Bio
lo
i
d
Hu
m
a
n
o
i
d
Ro
b
o
t,
”
2
0
1
8
1
5
t
h
In
t
.
Co
n
f.
Co
n
tro
l.
A
u
to
m.
Ro
b
o
t.
Vi
sio
n
,
ICA
RCV
2
0
1
8
,
p
p
.
5
4
-
5
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/ICAR
CV.2
0
1
8
.
8
5
8
0
6
3
3
.
[1
2
]
Riy
a
n
to
,
C
.
M
a
c
h
b
u
b
,
H.
Hi
n
d
e
rs
a
h
,
a
n
d
W.
A
d
ip
ra
wita,
“
S
lo
p
e
b
a
lan
c
in
g
stra
teg
y
fo
r
b
ip
e
d
a
l
ro
b
o
t
wa
lk
in
g
b
a
se
d
o
n
i
n
c
li
n
a
ti
o
n
e
stim
a
ti
o
n
u
sin
g
se
n
so
rs fu
si
o
n
,
”
In
t
.
J
.
El
e
c
tr.
E
n
g
.
In
fo
rm
a
t
ics
,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
5
2
7
-
5
4
7
,
2
0
1
9
.
[1
3
]
M
.
Ku
s
u
m
a
,
Riy
a
n
to
,
a
n
d
C.
M
a
c
h
b
u
b
,
“
Hu
m
a
n
o
id
Ro
b
o
t
P
a
th
P
lan
n
in
g
a
n
d
Re
ro
u
ti
n
g
Us
in
g
A
-
S
tar
S
e
a
rc
h
Alg
o
rit
h
m
,
”
Pro
c
.
-
2
0
1
9
IE
EE
In
t.
Co
n
f.
S
ig
n
a
ls S
y
st.
IC
S
ig
S
y
s 2
0
1
9
,
p
p
.
1
1
0
-
1
1
5
,
2
0
1
9
.
[1
4
]
H.
F
a
k
h
r
u
rro
ja,
A.
P
u
rwa
rian
ti
,
A.
S
.
P
ri
h
a
tma
n
to
,
a
n
d
C
.
M
a
c
h
b
u
b
,
“
I
n
teg
ra
ti
o
n
o
f
In
d
o
n
e
sia
n
S
p
e
e
c
h
a
n
d
Ha
n
d
G
e
stu
re
Re
c
o
g
n
it
i
o
n
fo
r
C
o
n
tro
ll
in
g
Hu
m
a
n
o
id
R
o
b
o
t,
”
i
n
2
0
1
8
1
5
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
n
tr
o
l,
Au
to
m
a
ti
o
n
,
Ro
b
o
ti
c
s
a
n
d
Vi
si
o
n
(ICAR
CV)
,
2
0
1
8
,
p
p
.
1
5
9
0
-
1
5
9
5
.
[1
5
]
H.
F
a
k
h
ru
rr
o
ja,
A.
S
.
P
rih
a
tma
n
to
,
a
n
d
C.
M
a
c
h
b
u
b
,
“
M
u
lt
imo
d
a
l
I
n
tera
c
ti
o
n
S
y
ste
m
fo
r
Ho
m
e
Ap
p
li
a
n
c
e
s
Co
n
tr
o
l,
”
I
n
t.
J
.
I
n
ter
a
c
t.
M
o
b
.
T
e
c
h
n
o
l
.
,
v
o
l
.
1
4
,
n
o
.
1
5
,
2
0
20.
[1
6
]
D.
A.
P
e
rm
a
tas
a
ri,
H.
F
a
k
h
ru
rr
o
ja,
a
n
d
C.
M
a
c
h
b
u
b
,
“
Hu
m
a
n
-
R
o
b
o
t
I
n
tera
c
ti
o
n
Ba
se
d
On
Dia
lo
g
M
a
n
a
g
e
m
e
n
t
Us
in
g
S
e
n
ten
c
e
S
imilarit
y
Co
m
p
a
riso
n
M
e
th
o
d
,
”
I
n
t.
J
.
Ad
v
.
S
c
i.
T
e
c
h
n
o
l
.
,
v
o
l
.
1
0
,
n
o
.
5
,
2
0
2
0
.
[1
7
]
E.
M
e
r
d
iv
a
n
,
D.
S
in
g
h
,
S
.
Ha
n
k
e
,
a
n
d
A.
Ho
l
z
in
g
e
r,
“
Dia
lo
g
u
e
S
y
ste
m
s
fo
r
I
n
telli
g
e
n
t
H
u
m
a
n
Co
m
p
u
ter
In
tera
c
ti
o
n
s,”
E
lec
tro
n
.
N
o
tes
T
h
e
o
r.
Co
m
p
u
t
.
S
c
i.
,
v
o
l.
3
4
3
,
p
p
.
5
7
-
7
1
,
2
0
1
9
.
[1
8
]
X.
Wan
g
a
n
d
C
.
Yu
a
n
,
“
Re
c
e
n
t
Ad
v
a
n
c
e
s
o
n
Hu
m
a
n
-
Co
m
p
u
ter
Dia
lo
g
u
e
,
”
CA
AI
T
ra
n
s.
I
n
tell.
T
e
c
h
n
o
l.
,
v
o
l.
1
,
n
o
.
4
,
p
p
.
3
0
3
-
3
1
2
,
2
0
1
6
.
[1
9
]
A.
Din
a
k
a
ra
m
a
n
i,
F
.
Ra
sh
e
l,
A.
Lu
t
h
fi,
a
n
d
R.
M
a
n
u
r
u
n
g
,
“
De
sig
n
i
n
g
a
n
I
n
d
o
n
e
sia
n
p
a
rt
o
f
s
p
e
e
c
h
tag
se
t
a
n
d
m
a
n
u
a
ll
y
ta
g
g
e
d
I
n
d
o
n
e
sia
n
c
o
rp
u
s,”
Pro
c
.
I
n
t.
C
o
n
f.
Asi
a
n
L
a
n
g
.
Pro
c
e
ss
.
2
0
1
4
,
IAL
P
2
0
1
4
,
p
p
.
6
6
-
6
9
,
2
0
1
4
.
[2
0
]
F
.
Ra
sh
e
l,
“
In
d
o
n
e
sia
Tag
g
e
d
C
o
rp
u
s,
”
De
sig
n
i
n
g
a
n
In
d
o
n
e
sia
n
Pa
rt
o
f
s
p
e
e
c
h
T
a
g
se
t
a
n
d
M
a
n
u
a
ll
y
T
a
g
g
e
d
In
d
o
n
e
sia
n
Co
r
p
u
s
.
[On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
g
it
h
u
b
.
c
o
m
/fam
ra
sh
e
l/
id
n
-
tag
g
e
d
-
c
o
r
p
u
s.
[2
1
]
A.
S
.
Rizk
i,
A.
T
jah
y
a
n
to
,
a
n
d
R.
Tri
a
li
h
,
“
Co
m
p
a
riso
n
o
f
ste
m
m
in
g
a
lg
o
ri
th
m
s
o
n
In
d
o
n
e
sia
n
t
e
x
t
p
ro
c
e
ss
in
g
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
,
C
o
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
9
5
–
1
0
2
,
2
0
1
9
.
[2
2
]
S
.
Yi
a
n
d
K.
Ju
n
g
,
“
A
Ch
a
t
b
o
t
b
y
C
o
m
b
i
n
in
g
F
i
n
it
e
S
tate
M
a
c
h
in
e
,
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l,
a
n
d
B
o
t
-
In
it
iativ
e
S
trate
g
y
,
”
A
lex
a
Price
Pro
c
.
,
p
p
.
1
-
1
0
,
2
0
1
7
.
[2
3
]
P
.
S
h
a
h
,
D.
Ha
k
k
a
n
i
-
Tü
r
,
a
n
d
L.
He
c
k
,
“
In
tera
c
ti
v
e
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
fo
r
tas
k
-
o
ri
e
n
ted
d
ialo
g
u
e
m
a
n
a
g
e
m
e
n
t,
”
NIPS
W
o
rk
.
,
n
o
.
i,
p
.
1
1
,
2
0
1
6
.
[2
4
]
E.
F
e
rre
ira
a
n
d
F
.
Lefè
v
re
,
“
Re
in
fo
rc
e
m
e
n
t
-
lea
rn
in
g
b
a
se
d
d
ia
l
o
g
u
e
sy
ste
m
fo
r
h
u
m
a
n
-
ro
b
o
t
in
t
e
ra
c
ti
o
n
s
wit
h
so
c
ially
-
in
s
p
ired
re
wa
rd
s,”
C
o
mp
u
t.
S
p
e
e
c
h
L
a
n
g
.
,
v
o
l.
3
4
,
n
o
.
1
,
p
p
.
2
5
6
-
2
7
4
,
2
0
1
5
.
[2
5
]
S
.
S
e
n
d
a
ri,
A
.
N.
Afa
n
d
i,
I.
A
.
E.
Zae
n
i,
Y.
D.
M
a
h
a
n
d
i,
K.
Hi
ra
sa
wa
,
a
n
d
H.
I.
Li
n
,
“
E
x
p
l
o
ra
t
io
n
o
f
g
e
n
e
ti
c
n
e
two
rk
p
r
o
g
ra
m
m
in
g
with
two
-
sta
g
e
re
in
fo
rc
e
m
e
n
t
lea
rn
in
g
f
o
r
m
o
b
i
le
ro
b
o
t,
”
T
EL
KOM
NIK
A
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
1
4
4
7
-
1
4
5
4
,
2
0
1
9
.
[2
6
]
R.
S
.
S
u
tt
o
n
,
Rein
fo
rc
e
me
n
t
lea
rn
in
g
:
a
n
in
tr
o
d
u
c
ti
o
n
,
S
e
c
o
n
d
.
Ca
m
b
rid
g
e
,
M
A:
T
h
e
M
IT
P
re
ss
,
2
0
1
8
.
[2
7
]
M
.
I.
Ah
m
a
d
,
O
.
M
u
b
i
n
,
a
n
d
J.
Orla
n
d
o
,
“
A
sy
ste
m
a
ti
c
re
v
iew
o
f
a
d
a
p
ti
v
it
y
i
n
h
u
m
a
n
-
ro
b
o
t
in
tera
c
ti
o
n
,
”
M
u
lt
im
o
d
a
l
T
e
c
h
n
o
l.
I
n
ter
a
c
t.
,
v
o
l.
1
,
n
o
.
3
,
2
0
1
7
.
[2
8
]
M
.
I.
Ah
m
a
d
,
O.
M
u
b
i
n
,
a
n
d
J.
Orla
n
d
o
,
“
Ad
a
p
ti
v
e
S
o
c
ial
Ro
b
o
t
fo
r
S
u
sta
in
in
g
S
o
c
ial
En
g
a
g
e
m
e
n
t
d
u
ri
n
g
Lo
n
g
-
Term
Ch
il
d
re
n
–
Ro
b
o
t
In
tera
c
ti
o
n
,
”
In
t.
J
.
Hu
m.
C
o
mp
u
t.
I
n
ter
a
c
t.
,
v
o
l.
3
3
,
n
o
.
1
2
,
p
p
.
9
4
3
-
9
6
2
,
2
0
1
7
.
[2
9
]
I.
Leite,
G
.
Ca
ste
ll
a
n
o
,
A
.
P
e
re
ira,
C.
M
a
rti
n
h
o
,
a
n
d
A
.
P
a
i
v
a
,
“
Emp
a
th
ic
Ro
b
o
ts
fo
r
Lo
n
g
-
te
rm
In
tera
c
ti
o
n
:
Ev
a
lu
a
t
i
n
g
S
o
c
ial
P
re
se
n
c
e
,
E
n
g
a
g
e
m
e
n
t
a
n
d
P
e
rc
e
iv
e
d
S
u
p
p
o
r
t
in
Ch
i
ld
re
n
,
”
In
t.
J
.
S
o
c
.
Ro
b
o
t.
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
3
2
9
-
3
4
1
,
2
0
1
4
.
[3
0
]
Ro
b
o
ti
s,
“
Ro
b
o
ti
s
e
-
M
a
n
u
a
l
Bi
o
l
o
id
G
P
.
”
[On
l
in
e
].
Av
a
il
a
b
le
:
h
tt
p
s:/
/em
a
n
u
a
l.
ro
b
o
t
is.co
m
/d
o
c
s/e
n
/ed
u
/
b
io
lo
i
d
/g
p
/
#
re
fe
re
n
c
e
s.
[A
c
c
e
ss
e
d
:
0
6
-
M
a
r
-
2
0
2
0
]
.
[3
1
]
D.
Ba
rn
a
rd
,
“
Av
e
ra
g
e
S
p
e
a
k
in
g
Ra
te
a
n
d
W
o
r
d
s
p
e
r
M
in
u
te,”
2
0
1
8
.
[On
l
in
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/v
irt
u
a
lsp
e
e
c
h
.
c
o
m
/
b
lo
g
/av
e
ra
g
e
-
sp
e
a
k
in
g
-
ra
te
-
wo
r
d
s
-
p
e
r
-
m
in
u
te.
[Ac
c
e
s
se
d
:
1
2
-
Ju
l
-
2
0
2
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.