A stabilizing reinforcement learning approach for sampled systems with partially unknown models.
Lukas BeckenbachPavel OsinenkoStefan StreifPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- complex systems
- mathematical models
- statistical models
- genetic algorithm
- function approximation
- probabilistic model
- machine learning
- parameter estimation
- learning systems
- computer systems
- state space
- markov decision processes
- computational models
- control strategies
- trading systems
- physical systems
- analytical models