Policy Gradient for Coherent Risk Measures.
Aviv TamarYinlam ChowMohammad GhavamzadehShie MannorPublished in: CoRR (2015)
Keyphrases
- risk measures
- policy gradient
- reinforcement learning
- function approximation
- optimal control
- gradient method
- risk averse
- reinforcement learning algorithms
- approximation methods
- reinforcement learning methods
- multistage
- variance reduction
- single agent
- robust optimization
- portfolio optimization
- state action
- average reward
- state space
- evolutionary algorithm
- machine learning
- multi agent
- markov decision processes
- dynamic programming