Policy Gradient for Coherent Risk Measures.
Aviv TamarYinlam ChowMohammad GhavamzadehShie MannorPublished in: NIPS (2015)
Keyphrases
- risk measures
- policy gradient
- gradient method
- function approximation
- reinforcement learning
- optimal control
- risk averse
- approximation methods
- reinforcement learning algorithms
- portfolio selection
- variance reduction
- single agent
- average reward
- reinforcement learning methods
- portfolio optimization
- sample size
- linear programming
- probability distribution
- machine learning