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!
Hi! Initially thanks for the contribution for ns3-ai.
Recently I'm trying to realize a DRL algorithm in WiFi scenario. But it took me too much time to produce enough tracks in experience pool to train the NN.So is there any possible that I can running multiple ns3 scripts with the same WiFi scenario configurations and interact with a single python script that maintains my DRL network, so I can foster my training process(In a word, I want to put my DQN in multiple ns-3 scripts simultaneously to get more data set to train the NN)?
Hi! Initially thanks for the contribution for ns3-ai. Recently I'm trying to realize a DRL algorithm in WiFi scenario. But it took me too much time to produce enough tracks in experience pool to train the NN.So is there any possible that I can running multiple ns3 scripts with the same WiFi scenario configurations and interact with a single python script that maintains my DRL network, so I can foster my training process(In a word, I want to put my DQN in multiple ns-3 scripts simultaneously to get more data set to train the NN)?