Long-Horizon Route-Constrained Policy for Learning Continuous Control Without Exploration.

Ruidong Cao Min Dong Xuanlu Jiang Sheng Bi Ning Xi

Published in: ICANN (2) (2022)

Keyphrases

action selection
reinforcement learning
prior knowledge
learning algorithm
mobile learning
autonomous learning
learning process
knowledge acquisition
learning tasks
active learning
control system
online learning
control method
inductive inference
adaptive control