A neural network scheme approximates risk and policies for dynamic risk-sensitive MDPs using synthetic data based on mean-variance risk estimation.
Q-learning for risk-sensitive control,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Scheme for Dynamic Risk-Sensitive Sequential Decision Making
A neural network scheme approximates risk and policies for dynamic risk-sensitive MDPs using synthetic data based on mean-variance risk estimation.