Convergence of synchronous reinforcement learning with linear function approximation.
Artur MerkeRalf SchoknechtPublished in: ICML (2004)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference learning
- temporal difference
- state action space
- mountain car
- radial basis function
- tile coding
- model free
- reinforcement learning algorithms
- learning tasks
- temporal difference methods
- optimal policy
- td learning
- state space
- knn
- machine learning
- k nearest neighbor
- convergence rate
- reinforcement learning methods
- markov decision problems
- policy search
- policy iteration
- neural network
- dynamical systems
- transfer learning