Policy Gradient Methods for Reinforcement Learning with Function Approximation.
Richard S. SuttonDavid A. McAllesterSatinder P. SinghYishay MansourPublished in: NIPS (1999)
Keyphrases
- function approximation
- policy gradient methods
- natural actor critic
- reinforcement learning
- policy gradient
- function approximators
- actor critic
- temporal difference
- reinforcement learning problems
- reinforcement learning algorithms
- model free
- state space
- reinforcement learning methods
- temporal difference learning
- control problems
- learning tasks
- learning algorithm
- multi agent
- optimal policy
- neuro fuzzy
- radial basis function
- approximation methods
- markov decision processes
- dynamic programming
- transfer learning
- supervised learning
- semi supervised
- machine learning