Deep Reinforcement Learning Based Quadrotor Control with Low Function Approximation Errors.
Zihao ZhangZhenlin LuYongzheng RenJinye RongShuai WangShikai SunPublished in: PEAI (2024)
Keyphrases
- function approximation
- reinforcement learning
- control problems
- temporal difference
- policy search methods
- temporal difference learning
- temporal difference learning algorithms
- function approximators
- mountain car
- model free
- learning tasks
- radial basis function
- optimal control
- control system
- adaptive control
- control strategies
- control method
- learning algorithm
- reinforcement learning algorithms
- control policy
- supervised learning
- td learning
- decision trees
- control strategy
- multi agent
- monte carlo
- feedback control
- transfer learning