Concatenated Dynamic Reinforcement Learning for Multi-staged Tasks (MST).

Yendo Hu Xue Bai Weijie Yang Yiliang Wu

Published in: EITCE (2021)

Keyphrases

reinforcement learning
dynamic environments
transfer learning
multi agent
feature vectors
learning process
state space
temporal difference
dynamically changing
real world
machine learning
feature extraction
optimal policy
multi agent environments