A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients.
Ivo GrondmanLucian BusoniuGabriel A. D. LopesRobert BabuskaPublished in: IEEE Trans. Syst. Man Cybern. Part C (2012)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- approximate dynamic programming
- reinforcement learning algorithms
- optimal control
- policy gradient methods
- gradient method
- policy iteration
- function approximation
- neuro fuzzy
- average reward
- optimal policy
- action selection
- model free
- markov decision processes
- state space
- dynamic programming
- decision problems
- finite state
- rl algorithms
- reinforcement learning methods
- temporal difference learning
- state action
- machine learning
- evaluation function
- linear program
- dynamical systems
- monte carlo
- learning algorithm