Comparing actor-critic deep reinforcement learning controllers for enhanced performance on a ball-and-plate system.
Daniel UdekweOre-ofe AjayiOsichinaka UbadikeKumater TerEmmanuel OkaforPublished in: Expert Syst. Appl. (2024)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- policy gradient
- function approximation
- approximate dynamic programming
- optimal control
- model free
- policy iteration
- state space
- gradient method
- markov decision processes
- neuro fuzzy
- adaptive control
- rl algorithms
- partially observable
- policy gradient methods
- control problems
- supervised learning
- multi agent
- machine learning
- learning problems
- dynamical systems
- optimal policy
- temporal difference learning
- reinforcement learning methods
- natural actor critic
- control law
- function approximators
- average reward
- dynamic programming
- learning algorithm
- reinforcement learning problems