Cross validation over discount 5k

Number of epochs: 5000

Rewards are limited by a lower and upper limit. This might cause problems.

training.simrunner.RewardHandlerName.consider-all

Considers all sensors.
Calculates a reward after every step.

Positive rewarded actions.

• Agent collides with the opponent consciously.
• Agent pushes the opponent from the field conscoiusly.

Negative rewarded actions.

• The agent moves from the field unforced. TODO find out reward values
• The agent is pushed from the field.

Rewards are calculated after every step and might be different from zero.

training.parallel.ParallelConfig.q-disc-0

Results for: Q0-DISC0 L0E0D0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D1

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D2

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D3

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D4

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D5

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10

Results for: Q0-DISC0 L0E0D6

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10