On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning.
Patrick GoetzShailesh KumarRisto MiikkulainenPublished in: ICML (1996)
Keyphrases
- reinforcement learning
- adaptation process
- function approximation
- high frequency
- learning algorithm
- markov decision processes
- high power
- signal detection
- optimal policy
- adaptation strategies
- wavelet analysis
- frequency domain
- signal processing
- learning process
- multi agent
- non stationary
- supervised learning
- model free
- dynamic programming
- image processing
- optimal control
- communication systems
- reinforcement learning algorithms
- learning capabilities
- multiresolution
- ofdm system
- policy search