Simon Chauvin

is it possible to edit, i.e. modify and save a .fit?

1

So far I can "decode" `.fit` files and export them e.g. in `.json`. Then I can easily modify the `.json`. I would like now to save the modified `.json` back...

can't convert complex to float

1

Thank you for this great code! Just one question regarding the line 16 of `prioritized_memory.py`: Should not **the absolute value of the TD-error** be taken in `return (error + self.e)...

my question: how can I **test an agent trained with a non-default `cfg/task/XXX.yaml` config?** --- I have trained two agents on the `FrankaCubeStack` task: - Agent1 with - the default...

Hi, thanks for this great notebook! At the bottom line, you miswrote `return`: `reutrn F.log_softmax(x)`