Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations.
Pavel TashevStefan PetrovFriederike MetzMarin BukovPublished in: CoRR (2024)
Keyphrases
- partial observations
- partially observable
- reinforcement learning
- belief state
- state space
- markov decision processes
- action models
- decision problems
- learning algorithm
- state variables
- partially observable markov decision processes
- dynamic programming
- dynamical systems
- transfer learning
- optimal control
- transition probabilities
- infinite horizon
- orders of magnitude
- markov chain
- supervised learning
- active learning
- spatio temporal
- bayesian networks
- machine learning