Deep-Reinforcement-Learning-Based Autonomous UAV Navigation With Sparse Rewards.
Chao WangJian WangJingjing WangXudong ZhangPublished in: IEEE Internet Things J. (2020)
Keyphrases
- reinforcement learning
- unmanned aerial vehicles
- land vehicle
- autonomous vehicles
- autonomous navigation
- path planning
- markov decision processes
- autonomous learning
- state space
- function approximation
- reinforcement learning algorithms
- multi agent
- cooperative
- high dimensional
- sparse data
- learning capabilities
- service robots
- sparse representation
- search and rescue
- optimal policy
- navigation systems
- compressive sensing
- learning algorithm
- vision based navigation
- supervised learning
- dynamic programming
- autonomous control
- robot navigation
- model free
- indoor environments
- obstacle avoidance
- reward shaping
- robot control
- control algorithm
- policy iteration
- mobile robot
- machine learning
- autonomous underwater vehicles
- state and action spaces
- real robot
- adaptive control
- robotic systems
- learning problems
- transfer learning