Combining system identification with reinforcement learning-based MPC.
Andreas B. MartinsenAnastasios M. LekkasSebastien GrosPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- input output
- function approximation
- real time
- genetic algorithm
- temporal difference
- optimal control
- hidden markov models
- dynamic programming
- markov decision processes
- reinforcement learning methods
- temporal difference learning
- markov decision process
- model free
- dynamic model
- closed loop
- optimal policy
- learning process
- search space
- case study
- search engine
- learning algorithm
- machine learning
- real world
- databases