Isn't param "--use_gate" important for Pong? #18
Description
Hey, in the paper StablizingTransformer..., there is a gate unit in the moudle of the GTrxl, but in your default params, the --use_gate is False. Why?
{{ message }}
Hey, in the paper StablizingTransformer..., there is a gate unit in the moudle of the GTrxl, but in your default params, the --use_gate is False. Why?