Looks Like Great Fun !
Hello! Your videos are really helpful to me lately! If possible I have a question : Where can I modify the rewards? Is it in the environment directly? I need to create an environment for an autonomous mobil robot with LIDARS and I need a different type of reward but I'm kind of lost...
Do you have a discord or something where we can ask questions? I am getting some very strange outputs for my average reward graph. Additionally, my new best reward is struggling to pass 200. Also would you be able to post your source code somewhere so we can compare? I just want to see where our code deviates (if at all). Thanks! Great series so far :D Edit: I tweaked my hyperparameters and now I am getting a much better result! I am new to machine learning so I am getting used to having to play with things like hyperparameters in order to get better results.
My model doesn't seem to learn anything at all. I've tweaked the hyperparameters and even tried using the same as the DQN model from stable-baselines, but it's not learning anything. Same thing happened when I tried to use your model.
@johnnycode