Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation.
Thanh LamArun VermaBryan Kian Hsiang LowPatrick JailletPublished in: ICLR (2023)
Keyphrases
- risk measures
- function approximation
- reinforcement learning
- temporal difference
- model free
- temporal difference learning
- function approximators
- risk averse
- radial basis function
- learning tasks
- state space
- reinforcement learning algorithms
- machine learning
- portfolio optimization
- linear combination
- learning algorithm
- reinforcement learning problems
- optimal policy
- robust optimization
- dynamic programming
- td learning
- transfer learning
- action selection
- reward function
- machine learning algorithms
- genetic algorithm
- policy gradient
- neural network