Trustworthy Policy Learning under the Counterfactual No-Harm Criterion.

Haoxuan Li Chunyuan Zheng Yixiao Cao Zhi Geng Yue Liu Peng Wu

Published in: ICML (2023)

Keyphrases

learning tasks
learning systems
learning process
artificial neural networks
prior knowledge
supervised learning
online learning
data sets
learning problems
learning community
unsupervised learning
actor critic
action selection
learning scheme
learning analytics
management system
active learning
neural network