QLOW03 Very low values for L and E 30k epochs

Problem QRW7: Results still too unstable.

Goal: Find better values for L and E based on the results of QRW07

training.parallel.ParallelConfig.q-low-0

L0 L1
learning rate 0.001 0.0001
E0 E1
epsilon 0.001 0.0001
D0
discount 0.3
M0
mapping non-linear-3
R0 R1 R2
reward handler speed-bonus speed-bonus speed-bonus

Results for: QLOW03 L0E0D0M0R0

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: QLOW03 L0E0D0M0R1

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: QLOW03 L0E0D0M0R2

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: QLOW03 L0E1D0M0R0

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: QLOW03 L0E1D0M0R1

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: QLOW03 L0E1D0M0R2

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: QLOW03 L1E0D0M0R0

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: QLOW03 L1E0D0M0R1

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: QLOW03 L1E0D0M0R2

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: QLOW03 L1E1D0M0R0

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: QLOW03 L1E1D0M0R1

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: QLOW03 L1E1D0M0R2

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