Open paapu88 opened 6 months ago
I'm looking into this and will get back to you.
@paapu88 is your observation space an image or a video with your environment?
@BillMatrix see https://www.gymlibrary.dev/environments/box2d/car_racing/#
I think the error is because you are using a VanillaQValueNetwork which requires the state and the action to have the same dimension. For image inputs, you want to use the CNNQValueNetwork as the network type (we need to enable that for deep q learning).
We are going to implement a fix.
Dear Developers, I'm getting the following error when running the code below
Am I doing something stupid, or is there some limitation (for instance, so that dimension of the action and observation space must be the same?) Terveisin, Markus