Agent learns but fairly well

[ghorbelm]

Hello
firstly, thank you for this tutorial.
I succeeded in making the train_dqn run but the training did not lead to a good result.

Game number: 005100 Frame number: 01981609 Average reward: 22.1 Time taken: 38.0s

Is this normal ?
Do you have any suggestions ?

Thanks

[ghorbelm]

Sorry
I just saw the dqn_fix.
I test it and I will tell you the results

[ghorbelm]

Thanks for you :) this a nice job

This is the results of my simulation :

Game number: 010590 Frame number: 07943478 Average reward: 115.7 Time taken: 69.4s
Game number: 010600 Frame number: 07958788 Average reward: 118.1 Time taken: 92.3s
Game number: 010610 Frame number: 07974828 Average reward: 134.0 Time taken: 65.2s
Game number: 010620 Frame number: 07989387 Average reward: 130.8 Time taken: 72.3s
Game number: 010630 Frame number: 08004983 Average reward: 124.8 Time taken: 61.2s
Game number: 010640 Frame number: 08021668 Average reward: 165.2 Time taken: 88.2s
Game number: 010650 Frame number: 08037870 Average reward: 183.3 Time taken: 88.8s
Evaluation score: 124.42857142857143