Improving Flight of Crazyflie Quadcopters Using Online Reinforcement Learning.
Steven ComandiniDrew ShambaughYufeng LuJing WangPublished in: MWSCAS (2023)
Keyphrases
- reinforcement learning
- online learning
- function approximation
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- real time
- supervised learning
- dynamic programming
- markov decision processes
- learning process
- optimal control
- model free
- information systems
- cross cultural
- online algorithms
- space shuttle
- balancing exploration and exploitation