Addressing Action Oscillations through Learning Policy Inertia.

Chen Chen Hongyao Tang Jianye Hao Wulong Liu Zhaopeng Meng

Published in: CoRR (2021)

Keyphrases

neural network
prior knowledge
learning systems
reinforcement learning
learning process
action selection
state action
learning scenarios
online learning
optimal policy
learning from experience
learning tasks
mobile learning
background knowledge
supervised learning
active learning
knowledge base
learning algorithm