Kaixhin / Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning
MIT License
1.56k stars 282 forks source link

load a model #69

Closed zyzhang1130 closed 4 years ago

zyzhang1130 commented 4 years ago

Hi, Can I check that is it necessary to run line 36-44 in agent.py every single time after I load a saved a model by line 24-31?

Thank you.

Kaixhin commented 4 years ago

Some lines are definitely necessary, others I'm not so sure about, but I run them all to be safe.