Factored Adaptation for Non-Stationary Reinforcement Learning.
Fan FengBiwei HuangKun ZhangSara MagliacanePublished in: CoRR (2022)
Keyphrases
- object detection
- non stationary
- reinforcement learning
- state space
- computer vision
- adaptation process
- factored markov decision processes
- optimal policy
- temporal evolution
- function approximation
- empirical mode decomposition
- blind source separation
- model free
- autoregressive
- markov decision processes
- machine learning
- adaptive algorithms
- particle filter
- white noise
- image processing
- learning algorithm
- concept drift
- financial time series