QED7 Epsilon decay big decay 10k

Find the optimal epsilon decay for decay of 1000 and 3000 epochs

training.parallel.ParallelConfig.q-ed-3

Cross validation for epsilon decay with big decay. 20% 10% and 5% of the inital epsilon

L0 L1 L2 L3
learning rate 0.2 0.2 0.2 0.2
E0
epsilon 0.05
ED0 ED1 ED2
epsilon decay decay-1000-20 decay-1000-10 decay-1000-05
ED3 ED4 ED5
decay-3000-20 decay-3000-10 decay-3000-05
D0
discount 0.3
M0
mapping non-linear-3
R0
reward handler can-see
F0
fetch mode eager

L0 E0 ED0 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L0 E0 ED1 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L0 E0 ED2 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L0 E0 ED3 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L0 E0 ED4 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L0 E0 ED5 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED0 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED1 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED2 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED3 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED4 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L1 E0 ED5 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED0 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED1 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED2 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED3 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED4 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L2 E0 ED5 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED0 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED1 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED2 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED3 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED4 D0 M0 R0 F0

q-values
video 0 video 1 video 2 video 3
video 4 video 5 video 6 video 7
video 8 video 9 video 10
L3 E0 ED5 D0 M0 R0 F0

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