# Data Set For MA Tiger, Baris Eker

discount: 0.9
agents: 2
values: reward
states: SL SR
actions: OpenLeft OpenRight Listen, OpenLeft OpenRight Listen
observations: HL HR, HL HR

T: OpenRight OpenLeft
0.5 0.5
0.5 0.5

T: OpenRight OpenRight
0.5 0.5
0.5 0.5

T: OpenRight Listen
0.5 0.5
0.5 0.5

T: OpenLeft OpenLeft
0.5 0.5
0.5 0.5

T: OpenLeft OpenRight
0.5 0.5
0.5 0.5

T: OpenLeft Listen
0.5 0.5
0.5 0.5

T: Listen OpenLeft
0.5 0.5
0.5 0.5

T: Listen OpenRight
0.5 0.5
0.5 0.5

T: Listen Listen
1 0
0 1

O: Listen Listen SL
0.85 0.15
0.85 0.15

O: Listen Listen SR
0.15 0.85
0.15 0.85

O: OpenLeft OpenLeft *
0.5 0.5
0.5 0.5

O: OpenLeft OpenRight *
0.5 0.5
0.5 0.5

O: OpenLeft Listen *
0.5 0.5
0.5 0.5

O: OpenRight OpenLeft *
0.5 0.5
0.5 0.5

O: OpenRight OpenRight *
0.5 0.5
0.5 0.5

O: OpenRight Listen *
0.5 0.5
0.5 0.5

O: Listen OpenLeft *
0.5 0.5
0.5 0.5

O: Listen OpenRight *
0.5 0.5
0.5 0.5

R: OpenRight OpenRight SL 20
R: OpenLeft OpenLeft SL -50
R: OpenRight OpenLeft SL -100
R: OpenLeft OpenRight SL -100
R: Listen Listen SL -2
R: Listen OpenRight SL +9
R: OpenRight Listen SL +9
R: Listen OpenLeft SL -101
R: OpenLeft Listen SL -101

R: OpenRight OpenRight SR -50
R: OpenLeft OpenLeft SR 20
R: OpenRight OpenLeft SR -100
R: OpenLeft OpenRight SR -100
R: Listen Listen SR -2
R: Listen OpenRight SR -101
R: OpenRight Listen SR -101
R: Listen OpenLeft SR 9
R: OpenLeft Listen SR 9