Deep Deterministic Policy Gradient for Navigation of Mobile Robots.
Junior Costa de JesusJair Augusto BottegaMarco Antônio De Souza Leite CuadrosDaniel Fernando Tello GamarraPublished in: J. Intell. Fuzzy Syst. (2021)
Keyphrases
- mobile robot
- policy gradient
- obstacle avoidance
- path planning
- parametric optimization
- reinforcement learning
- actor critic
- gradient method
- function approximation
- optimal control
- dynamic environments
- autonomous robots
- single agent
- multi robot
- model free reinforcement learning
- state action
- reinforcement learning algorithms
- approximation methods
- partially observable markov decision processes
- motion planning