Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward.

Haoxin Lin Hongqiu Wu Jiaji Zhang Yihao Sun Junyin Ye Yang Yu

Published in: CoRR (2023)

Keyphrases

reinforcement learning
decomposition method
database
information systems
trajectory data
neural network
expert systems
long run
image processing
image segmentation
image decomposition
hierarchical decomposition
trajectory planning