Convergent Combinations of Reinforcement Learning with Linear Function Approximation.
Ralf SchoknechtArtur MerkePublished in: NIPS (2002)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- tile coding
- temporal difference learning
- mountain car
- model free
- radial basis function
- state action space
- td learning
- learning tasks
- neural network
- reinforcement learning algorithms
- state space
- data mining
- fixed point
- temporal difference methods
- reinforcement learning problems
- knn
- active learning
- learning process
- action space
- transfer learning
- markov decision processes