issues
search
exalearn
/
EXARL
Scalable Framework for Reinforcement Learning
Other
10
stars
5
forks
source link
ExaRL tasks
#241
Open
tcfuji
opened
2 years ago
tcfuji
commented
2 years ago
Made
update_target
method agent specific and not exposed to workflow. It's now used inside the train call.
Made a common folder and separated out models and replay buffers. Agent vault only has agents.
Moved epsilon to agents.
Include PER beta.
This PR builds off of the develop_sept_22 branch.
update_targetmethod agent specific and not exposed to workflow. It's now used inside the train call.This PR builds off of the develop_sept_22 branch.