search

MishaLaskin / curl

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
MIT License
561 stars 88 forks source link

I know the issue will get no reply , but where is the moco in the code? #29

Open ItsBean opened 1 year ago

ItsBean commented 1 year ago

I understand that the response might be delayed, but I'm having difficulty locating the MoCo implementation in the CURL codebase. Could you kindly point me to the relevant section or file where MoCo is implemented? Thank you for your assistance.

LiuZhenxian123 commented 3 months ago

I understand that the response might be delayed, but I'm having difficulty locating the MoCo implementation in the CURL codebase. Could you kindly point me to the relevant section or file where MoCo is implemented? Thank you for your assistance.

the critic_target is the momentum-updated encoder,since critic_target's parameter is udpated in an EMA manner.