Start
Stop
Reset
Game settings
Sim speed:
12
episodes/sec
1
20
Fruit count:
2
total
1
12
Starting position:
Random
Standard
Random
Custom
Board mode:
Wrap-around
Solid
Wrap-around
Hyperparameters
Learning rate:
α
=
0.10
0.01
1
Discount factor:
γ
=
0.4
0.01
1
Policy function:
ε
=
0.2
0.01
1
Rewards
Eating fruit:
Dying:
Movement: