An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient.
Yudong LuoGuiliang LiuPascal PoupartYangchen PanPublished in: CoRR (2023)
Keyphrases
- risk averse
- policy gradient
- variance reduction
- risk neutral
- decision makers
- utility function
- stochastic programming
- portfolio management
- gradient method
- reinforcement learning
- function approximation
- bayesian networks
- decision making
- approximation methods
- reinforcement learning algorithms
- data mining
- monte carlo
- sample size
- machine learning