Exponential TD Learning: A Risk-Sensitive Actor-Critic Reinforcement Learning Algorithm.
Erfaun NooraniChristos N. MavridisJohn S. BarasPublished in: ACC (2023)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- model free
- evaluation function
- optimal control
- reinforcement learning algorithms
- step size
- average reward
- monte carlo
- policy gradient
- action selection
- markov decision processes
- policy iteration
- markov decision problems
- neural network
- real valued
- linear program
- long run
- supervised learning