Aligning an optical interferometer with beam divergence control and continuous action space.
Stepan MakarenkoDmitry SorokinAlexander E. UlanovA. I. LvovskyPublished in: CoRR (2021)
Keyphrases
- action space
- control policies
- state space
- markov decision processes
- real valued
- continuous state
- action selection
- reinforcement learning
- continuous state spaces
- continuous action
- control system
- state and action spaces
- dynamic environments
- control strategy
- decision making
- heuristic search
- expectation maximization
- function approximation
- optimal control
- probabilistic model
- stochastic processes
- markov decision process
- mobile robot
- objective function
- machine learning