Optimizing for the Future in Non-Stationary MDPs.
Yash ChandakGeorgios TheocharousShiv ShankarMartha WhiteSridhar MahadevanPhilip S. ThomasPublished in: ICML (2020)
Keyphrases
- non stationary
- markov decision processes
- adaptive algorithms
- long term
- finite horizon
- reinforcement learning
- state space
- concept drift
- stock price
- random fields
- blind source separation
- temporal evolution
- autoregressive
- empirical mode decomposition
- financial time series
- signal processing
- white noise
- object detection
- change point detection