A Novel Actor - Critic Motor Reinforcement Learning for Continuum Soft Robots.
Luis Pantoja-GarciaVicente Parra-VegaRodolfo García-RodríguezCarlos-Ernesto Vázquez-GarcíaPublished in: Robotics (2023)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- optimal control
- reinforcement learning algorithms
- real robot
- approximate dynamic programming
- function approximation
- gradient method
- neuro fuzzy
- mobile robot
- multi robot
- policy iteration
- state space
- robotic systems
- model free
- markov decision processes
- control problems
- average reward
- policy gradient methods
- reinforcement learning methods
- natural actor critic
- machine learning
- autonomous robots
- dynamic programming
- temporal difference learning
- multi agent
- step size
- transfer learning
- optimal policy
- sufficient conditions