Q-CV7 Cross validation reward at end

number of epochs: 20k

Rewards are no longer limited by a lower and upper limit.

Rewards are only calculated at the end of a simulation. Rewards on intermediate steps are zero.

The ranges for learning rate, epsilon and discount were chosen from the results of Q-CV4

training.simrunner.RewardHandlerName.end-consider-all

Considers all sensors.
Calculates a reward after every step.

Positive rewarded actions.

Negative rewarded actions.

Rewards are calculated only after the end of a match. All rewards before that are zero

training.parallel.ParallelConfig.q-cross-1

L0L1L2
learning rate0.70.80.9
E0E1E2
epsilon0.010.050.1
D0D1D2D3
discount0.950.990.9950.999

Results for: Q-CV7 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: Q-CV7 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: Q-CV7 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: Q-CV7 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: Q-CV7 L0E1D0

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: Q-CV7 L0E1D1

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: Q-CV7 L0E1D2

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: Q-CV7 L0E1D3

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: Q-CV7 L0E2D0

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: Q-CV7 L0E2D1

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: Q-CV7 L0E2D2

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: Q-CV7 L0E2D3

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: Q-CV7 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: Q-CV7 L1E0D1

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: Q-CV7 L1E0D2

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: Q-CV7 L1E0D3

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: Q-CV7 L1E1D0

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: Q-CV7 L1E1D1

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: Q-CV7 L1E1D2

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: Q-CV7 L1E1D3

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: Q-CV7 L1E2D0

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: Q-CV7 L1E2D1

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: Q-CV7 L1E2D2

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: Q-CV7 L1E2D3

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: Q-CV7 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: Q-CV7 L2E0D1

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: Q-CV7 L2E0D2

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: Q-CV7 L2E0D3

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: Q-CV7 L2E1D0

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: Q-CV7 L2E1D1

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: Q-CV7 L2E1D2

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: Q-CV7 L2E1D3

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: Q-CV7 L2E2D0

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: Q-CV7 L2E2D1

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: Q-CV7 L2E2D2

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: Q-CV7 L2E2D3

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