Control with adaptive Q-learning: A comparison for two classical control problems.
João Pedro AraújoMário A. T. FigueiredoMiguel Ayala BottoPublished in: Eng. Appl. Artif. Intell. (2022)
Keyphrases
- control problems
- reinforcement learning
- adaptive control
- optimal control
- continuous state spaces
- reinforcement learning methods
- control method
- state space
- cooperative
- queueing systems
- function approximation
- multi agent
- model free
- stochastic control
- nonlinear systems
- learning algorithm
- reinforcement learning algorithms
- dynamic programming
- markov decision processes
- optimal policy
- dynamic environments
- machine learning
- hamilton jacobi bellman