Basis Function Adaptation in Temporal Difference Reinforcement Learning.
Ishai MenacheShie MannorNahum ShimkinPublished in: Ann. Oper. Res. (2005)
Keyphrases
- temporal difference
- basis functions
- reinforcement learning
- state space
- function approximation
- linear combination
- radial basis function
- td learning
- reinforcement learning algorithms
- temporal difference learning
- model free
- evaluation function
- action selection
- policy evaluation
- step size
- function approximators
- actor critic
- temporal difference methods
- monte carlo
- policy iteration
- markov decision processes
- factored mdps
- transfer learning
- supervised learning
- learning algorithm
- neural network
- particle filter
- small number
- partially observable
- cost function
- markov decision problems
- genetic algorithm
- machine learning
- data mining