Potential Bug in 1dConv layer

[throwaway556]

I have installed keras-rl from pip today and encountered a bug in the process.

When trying to do 1D convolution keras doesn't accept an input layer with input_shape=(1,X), it must be input_shape=(X,1). I believe this is due to the 1d conv layer needing the data shaped a certain way in order to perform convolution. The size can't be greater than the input value, so when your shape is (1,X) but you have a size of 5 it doesn't translate the convolution to the X but rather the one.

I believe I have solved this specific issue but unfortunately it breaks the ability to accept(1,X). I am posting this to bring to the developers' attention for a better solution.

I have attached my openai gym file(block world) and two files for 1dconv and non-1dconv as well as a source file of what should be changed.

Thank you for creating this package and I hope you are able to resolve the issue.

[mirraaj]

@throwaway556 I am a bit busy these days. I will review this PR as soon as I get time. I appreciate your efforts to find the potential bug in the codes. Thanks