jerrodparker20 / adaptive-transformers-in-rl

Adaptive Attention Span for Reinforcement Learning
132 stars 14 forks source link

Isn't param "--use_gate" important for Pong? #18

Open weihongwei0586 opened 3 years ago

weihongwei0586 commented 3 years ago

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?