JunyeopLee

Hi @zhifanwu, Thank for your questions The aggregation method of found policy's probs and magnitudes is just summation of each value.

Hi @allenfutaki . Thank you for your question. ''My final question should be "why don't you merge the sub-policies into one but randomly choose?"'' \>\> I think that each sub-policy...

Hi, I'm sorry for the late comment. Now I see you left an issue. I tested the project only with python 3.6. Can you try with the lower version of...

Hi @jjjjohnson, Thanks for the comment. I think your comment is correct. There is no need to add self-attention bias "during inference", so self_attention_bias should be 1. I think [self_attention_bias[:,...