A Reinforcement Learning Method for Quadrotor Attitude Control Based on Expert Information.
Yalu ZhuShikang LianWentao ZhongWei MengPublished in: CACRE (2023)
Keyphrases
- prior knowledge
- reinforcement learning
- preprocessing
- high accuracy
- information extraction
- detection method
- cost function
- significant improvement
- statistical information
- data sets
- prior information
- model free
- expert knowledge
- mathematical model
- policy search
- pairwise
- multi agent
- support vector machine svm
- information sources
- video sequences
- image registration
- probabilistic model
- dynamic programming
- computational complexity