A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning.
Alborz GeramifardThomas J. WalshStefanie TellexGirish ChowdharyNicholas RoyJonathan P. HowPublished in: Found. Trends Mach. Learn. (2013)
Keyphrases
- function approximators
- reinforcement learning
- dynamic programming
- function approximation
- reinforcement learning algorithms
- markov decision problems
- temporal difference
- state space
- neural network
- reinforcement learning problems
- action space
- markov decision processes
- continuous state and action spaces
- temporal difference methods
- policy search
- optimal control
- state action
- learning tasks
- multi agent
- reinforcement learning methods
- learning algorithm
- model free
- partially observable
- optimal policy
- learning process
- linear programming
- least squares
- supervised learning
- continuous state
- dynamic environments
- feature selection
- td learning
- real valued
- transfer learning