Equivariant Reinforcement Learning for Quadrotor UAV.
Beomyeol YuTaeyoung LeePublished in: ACC (2023)
Keyphrases
- reinforcement learning
- aerial vehicles
- unmanned aerial vehicles
- function approximation
- model free
- vision based navigation
- temporal difference
- rotation invariant
- path planning
- reinforcement learning algorithms
- state space
- markov decision processes
- machine learning
- robotic control
- multi agent
- optimal policy
- action selection
- neural network
- dynamic environments
- robot control
- markov decision process
- temporal difference learning
- search and rescue
- matrix valued
- multiscale
- mission planning
- control algorithm