Interferobot: aligning an optical interferometer by a reinforcement learning agent.
Dmitry SorokinAlexander E. UlanovEkaterina A. SazhinaAlexander I. LvovskyPublished in: NeurIPS (2020)
Keyphrases
- learning agent
- reinforcement learning
- state space
- reinforcement learning algorithms
- learning algorithm
- solving problems
- learning capabilities
- selective perception
- learning process
- temporal difference
- markov decision processes
- single agent
- function approximation
- machine learning
- dynamic programming
- reward function
- model free
- learning tasks
- transfer learning
- action selection
- optimal policy
- multi agent
- fuzzy systems
- computational complexity
- input output
- learning experience
- multi agent systems
- search algorithm
- supervised learning