A multi-critic deep deterministic policy gradient UAV path planning.
Runjia WuFangqing GuJie HuangPublished in: CIS (2020)
Keyphrases
- path planning
- policy gradient
- actor critic
- mobile robot
- reinforcement learning
- optimal control
- gradient method
- dynamic environments
- unmanned aerial vehicles
- multi robot
- path planning algorithm
- function approximation
- single agent
- path finding
- aerial vehicles
- reinforcement learning algorithms
- optimal path
- approximation methods
- motion planning
- variance reduction
- autonomous vehicles
- average reward
- reinforcement learning methods
- approximate dynamic programming
- degrees of freedom
- temporal difference
- negative matrix factorization
- search and rescue
- simulated annealing
- evolutionary algorithm