In this repo I tried using Evolutionary Stratgies to train a neural network to play Super Mario Bros. for the NES. The generall approach of this type of machine learning can be found here.
| Training 28 uses Agent_old (no sprinting) | Training 42 uses the (new) Agent |
|---|---|
![]() |
![]() |
| Training 29 uses Agent_old (no sprinting) | Training 43 uses the (new) Agent |
|---|---|
![]() |
![]() |
| Training 41 uses the (new) Agent | Training 44 uses the (new) Agent |
|---|---|
![]() |
![]() |
| Training 45 uses the (new) Agent |
|---|
![]() |
| Training 48 uses the (new) Agent | From the same Trainingssession |
|---|---|
![]() |
![]() |








