search

jbr-ai-labs / mamba

This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".
MIT License
46 stars 9 forks source link

Potential duplication of the code in DreamerWorker.py #3

Closed GoingMyWay closed 2 years ago

GoingMyWay commented 2 years ago

Hi, I found this line is called twice. Is it a potential duplication of the code?

vladimirrim commented 2 years ago

Hi, no, we add two items here on purpose, this technique is called absorbing states (you can read more about it here. Basically we are adding a state that loops to itself