issues
search
facebookresearch
/
rlmeta
RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.
MIT License
284
stars
28
forks
source link
Fix bugs in ApeX DQN
#60
Closed
xiaomengy
closed
2 years ago
xiaomengy
commented
2 years ago
This PR fixed several issues in ApeX-DQN
Add global step_counter so control target_net sync frequency.
Fix a bug in SegmentTree when the size is exactly 2^n
This PR fixed several issues in ApeX-DQN