QMAP08 Check variance of equal parameters

Run multiple trainings with equal parameters explore the variance of training results.

training.simrunner.RewardHandlerName.continuous-consider-all

Considers all simulation events for calculating the reward.

Possible simulation events created for an agent:

  1. After every simulation step:

  2. At simulation end:

(t * x) is the 'speed bonus'

t = 1 - (s / max_s)

s:     Number of steps when th simulation ended   
max_s: Max number of steps for a simulation

Means, the reward/penalty is higher the shorter the simulation ran. The agent gets a higher reward when fast pushing out the opponent, or a higher penalty when fast moving unforced out of the field.

training.parallel.ParallelConfig.q-map-4

L0 L1 L2
learning rate 0.12 0.12 0.12

​ | E0 | E1 | E2
-------- | ----- | -----
epsilon | 0.015 | 0.015 | 0.015

D0 D1 D2
discount 0.3 0.3 0.3
M0 M1 M1
mapping non-linear-3 non-linear-3 non-linear-3

L0 E0 D0 M0

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 D0 M1

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 D0 M2

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 D1 M0

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 D1 M1

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 D1 M2

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 D2 M0

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 D2 M1

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 D2 M2

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 E1 D0 M0

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 E1 D0 M1

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 E1 D0 M2

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 E1 D1 M0

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 E1 D1 M1

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 E1 D1 M2

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 E1 D2 M0

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 E1 D2 M1

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 E1 D2 M2

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 E2 D0 M0

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 E2 D0 M1

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 E2 D0 M2

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 E2 D1 M0

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 E2 D1 M1

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 E2 D1 M2

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 E2 D2 M0

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 E2 D2 M1

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 E2 D2 M2

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 D0 M0

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 D0 M1

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 D0 M2

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 D1 M0

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 D1 M1

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 D1 M2

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 D2 M0

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 D2 M1

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 D2 M2

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 E1 D0 M0

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 E1 D0 M1

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 E1 D0 M2

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 E1 D1 M0

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 E1 D1 M1

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 E1 D1 M2

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 E1 D2 M0

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 E1 D2 M1

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 E1 D2 M2

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 E2 D0 M0

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 E2 D0 M1

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 E2 D0 M2

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 E2 D1 M0

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 E2 D1 M1

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 E2 D1 M2

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 E2 D2 M0

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 E2 D2 M1

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 E2 D2 M2

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 D0 M0

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 D0 M1

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 D0 M2

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 D1 M0

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 D1 M1

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 D1 M2

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 D2 M0

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 D2 M1

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 D2 M2

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 E1 D0 M0

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 E1 D0 M1

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 E1 D0 M2

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 E1 D1 M0

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 E1 D1 M1

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 E1 D1 M2

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 E1 D2 M0

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 E1 D2 M1

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 E1 D2 M2

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 E2 D0 M0

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 E2 D0 M1

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 E2 D0 M2

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 E2 D1 M0

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 E2 D1 M1

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 E2 D1 M2

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 E2 D2 M0

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 E2 D2 M1

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 E2 D2 M2

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