Addressing Action Oscillations through Learning Policy Inertia.

Chen Chen Hongyao Tang Jianye Hao Wulong Liu Zhaopeng Meng

Published in: AAAI (2021)

Keyphrases

learning algorithm
unsupervised learning
learning process
prior knowledge
online learning
action selection
learning systems
learning tasks
decision making
e learning
reinforcement learning
optimal policy
learning problems
learning scheme
state action
action models