Closed muzhizhao closed 1 year ago
I commented from https://github.com/harfang3d/dogfight-sandbox-hg2/blob/15b01ba9bd33a5ed2b08fdba8c6368d86c9ab833/source/main.py#L19 to line 28 and after added this code.
port = input('Port : ')
nwport = int(port)
netws.dogfight_network_port = nwport
when you run the code it will ask port number give different port numbers and in each starting different game you can run parallel training.
I commented from
to line 28 and after added this code.
port = input('Port : ')
nwport = int(port)
netws.dogfight_network_port = nwport
when you run the code it will ask port number give different port numbers and in each starting different game you can run parallel training.
Hello, I have some questions. Can you help me? Question one: the dogfight cannot obtain states of missiles launched by planes when we test client_sample_missile_custom_physics.py. There are some errors: "Nonetype" object has no attribute 'decode'. Question two: the dogfight are unable to reset airplanes to sky in the reset function including reset_machine(), reset_machine_matrix() and rearm_machine() after they are shot down or crashed. It is unfriendly to RL training. These questions confused me, thanks.
Hi, I am working on a reinforcement learning project using the Harfang platform and I would like to ask how to enable multiple dogfight-sandboxes in network mode to achieve parallel training?