Risk-Sensitive Reinforcement Learning Via Entropic- VaR Optimization.
Xinyi NiLifeng LaiPublished in: IEEECONF (2022)
Keyphrases
- risk sensitive
- reinforcement learning
- optimal control
- markov decision processes
- model free
- utility function
- optimization algorithm
- function approximation
- efficient optimization
- markov decision problems
- control policies
- state space
- reinforcement learning algorithms
- learning algorithm
- dynamic programming
- robust optimization
- markov decision process
- information theory
- optimal policy
- machine learning
- optimization methods
- learning tasks
- average cost
- stochastic optimization
- action space
- optimization problems
- probability distribution