QMAP02 Cross validation mapping

number of epochs: 20k

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

For the training start performance see: Training start performance

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-1

L0 L1 L2
learning rate 0.01 0.1 0.5
E0 E1
epsilon 0.01 0.1
D0 D1 D2
discount 0.4 0.6 0.9
M0 M1
mapping non-linear-1 non-linar-2

Results for: QMAP02 L0E0D0M0

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: QMAP02 L0E0D0M1

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: QMAP02 L0E0D1M0

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: QMAP02 L0E0D1M1

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: QMAP02 L0E0D2M0

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: QMAP02 L0E0D2M1

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: QMAP02 L0E1D0M0

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: QMAP02 L0E1D0M1

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: QMAP02 L0E1D1M0

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: QMAP02 L0E1D1M1

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: QMAP02 L0E1D2M0

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: QMAP02 L0E1D2M1

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: QMAP02 L1E0D0M0

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: QMAP02 L1E0D0M1

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: QMAP02 L1E0D1M0

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: QMAP02 L1E0D1M1

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: QMAP02 L1E0D2M0

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: QMAP02 L1E0D2M1

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: QMAP02 L1E1D0M0

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: QMAP02 L1E1D0M1

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: QMAP02 L1E1D1M0

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: QMAP02 L1E1D1M1

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: QMAP02 L1E1D2M0

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: QMAP02 L1E1D2M1

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: QMAP02 L2E0D0M0

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: QMAP02 L2E0D0M1

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: QMAP02 L2E0D1M0

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: QMAP02 L2E0D1M1

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: QMAP02 L2E0D2M0

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: QMAP02 L2E0D2M1

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: QMAP02 L2E1D0M0

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: QMAP02 L2E1D0M1

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: QMAP02 L2E1D1M0

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: QMAP02 L2E1D1M1

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: QMAP02 L2E1D2M0

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: QMAP02 L2E1D2M1

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