Reinforcement Learning for Mobile Robot Obstacle Avoidance with Deep Deterministic Policy Gradient.
Miao ChenWenna LiShihan FeiYufei WeiMingyang TuJiangbo LiPublished in: ICIRA (3) (2022)
Keyphrases
- obstacle avoidance
- policy gradient
- mobile robot
- reinforcement learning
- actor critic
- path planning
- function approximation
- reinforcement learning algorithms
- optimal control
- dynamic environments
- gradient method
- motion planning
- autonomous vehicles
- reinforcement learning methods
- policy gradient methods
- approximation methods
- multi robot
- single agent
- robotic systems
- variance reduction
- real robot
- partially observable markov decision processes
- state space
- neural network
- learning algorithm
- model free
- function approximators
- average reward
- robot control
- closed loop
- knowledge base