Enable the interaction between ns-3 and popular frameworks using Python, which mean you can train and test your AI algorithms in ns-3 without changing any frameworks you are using now!
The first very small patch makes sure to forward the ns3 settings variable to the simulation upon subsequent resets.
Then, we replace all invalid uses of self.aciton_space to spaceDesc instead. We guarantee correct implementation by declaring _pack_data a classmethod.
Lastly, we set the dtypes of the numpy arrays specifically. Alternativly, it is not correctly set: e.g. float32 gets converted to float64
The first very small patch makes sure to forward the ns3 settings variable to the simulation upon subsequent resets.
Then, we replace all invalid uses of
self.aciton_space
tospaceDesc
instead. We guarantee correct implementation by declaring_pack_data
a classmethod.Lastly, we set the dtypes of the numpy arrays specifically. Alternativly, it is not correctly set: e.g.
float32
gets converted tofloat64