Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning.
Jueming HuXuxi YangWeichang WangPeng WeiLei YingYongming LiuPublished in: CoRR (2021)
Keyphrases
- action space
- obstacle avoidance
- reinforcement learning
- mobile robot
- state space
- path planning
- markov decision processes
- state and action spaces
- real valued
- continuous state
- continuous state spaces
- visually guided
- action selection
- reinforcement learning methods
- stochastic processes
- motion planning
- autonomous vehicles
- state action
- reinforcement learning algorithms
- markov decision process
- continuous action
- function approximators
- function approximation
- single agent
- model free
- optimal policy
- markov decision problems
- learning algorithm
- dynamic environments
- dynamic programming
- policy search
- multi agent
- machine learning