Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- gradient method
- function approximation
- policy iteration
- neuro fuzzy
- markov decision processes
- model free
- state space
- control problems
- optimal policy
- rl algorithms
- policy gradient methods
- machine learning
- average reward
- cost function
- learning algorithm
- infinite horizon
- finite state
- temporal difference learning
- learning problems
- dynamic programming
- natural actor critic
- neural network