Fingerprint
Dive into the research topics of 'A multi-step on-policy deep reinforcement learning method assisted by off-policy policy evaluation'. Together they form a unique fingerprint.- Sort by
- Weight
- Alphabetically
A multi-step on-policy deep reinforcement learning method assisted by off-policy policy evaluation
Huaqing Zhang, Hongbin Ma*, Bemnet Wondimagegnehu Mersha, Ying Jin
*Corresponding author for this work
Research output: Contribution to journal › Article › peer-review