Deep Deterministic Policy Gradient for Navigation of Mobile Robots in Simulated Environments.
Junior Costa de JesusJair Augusto BottegaMarco Antônio De Souza Leite CuadrosDaniel Fernando Tello GamarraPublished in: ICAR (2019)
Keyphrases
- mobile robot
- policy gradient
- obstacle avoidance
- dynamic environments
- autonomous robots
- robotic systems
- path planning
- real robot
- parametric optimization
- motion planning
- multi robot
- approximation methods
- optimal control
- gradient method
- actor critic
- neural network
- model free reinforcement learning
- function approximation
- convergence rate
- heuristic search
- reinforcement learning
- computational complexity