DQNcar in PythonClient is not working (will not converge)

[QiyuZ]

There is an example in PythonClient which applies DQN to run the car. However, I ran it for a long time and found it will not converge. Does anyone success?

[mitchellspryn]

Not sure about the tutorial on this repo, but you may try ours here.

[zimmy87]

Hi @QiyuZ, thank you for reporting this issue. This script was recently removed in #3215 and replaced with a new script at \AirSim\PythonClient\reinforcement_learning\dqn_car.py that uses the new OpenAI gym wrapper. I tested the new script locally and it runs for me. Can you retest with the new script and report back if you see any issues?