Incremental Basis Construction from Temporal Difference Error.
Yi SunFaustino J. GomezMark B. RingJürgen SchmidhuberPublished in: ICML (2011)
Keyphrases
- temporal difference
- td learning
- reinforcement learning
- evaluation function
- function approximation
- model free
- monte carlo
- temporal difference learning
- action selection
- step size
- policy evaluation
- supervised learning
- temporal difference methods
- policy iteration
- reinforcement learning algorithms
- neural network
- function approximators
- radial basis function
- optimal policy
- data mining