Aligning an optical interferometer with beam divergence control and continuous action space.
Stepan MakarenkoDmitry Igorevich SorokinAlexander UlanovAlexander I. LvovskyPublished in: CoRL (2021)
Keyphrases
- action space
- control policies
- state space
- markov decision processes
- real valued
- reinforcement learning
- action selection
- state and action spaces
- continuous state
- stochastic processes
- continuous state spaces
- control system
- continuous action
- single agent
- electron beam
- control problems
- state action
- heuristic search
- orders of magnitude
- search space
- multi agent
- bayesian networks