Reinforcement Learning in Episodic Non-stationary Markovian Environments.
Samuel P. M. ChoiNevin Lianwen ZhangDit-Yan YeungPublished in: IC-AI (2004)
Keyphrases
- non stationary
- reinforcement learning
- adaptive algorithms
- blind source separation
- white noise
- autoregressive
- temporal evolution
- random fields
- concept drift
- empirical mode decomposition
- function approximation
- markov decision processes
- multiscale
- stock price
- dynamic environments
- state space
- image data
- change point detection