Cross validation over learning rate 10k

Number of epochs: 10000 Q_LR_1

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-lr-1

Results for: Q0-LR3 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-LR3 L1E0D0

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-LR3 L2E0D0

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-LR3 L3E0D0

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-LR3 L4E0D0

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