Designing a Robust Low-Level Agnostic Controller for a Quadrotor with Actor-Critic Reinforcement Learning.
Guilherme Siqueira EduardoWouter CaarlsPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- temporal difference
- policy gradient
- approximate dynamic programming
- reinforcement learning algorithms
- gradient method
- neuro fuzzy
- policy iteration
- function approximation
- lyapunov stability
- model free
- state space
- action selection
- learning algorithm
- control policy
- rl algorithms
- adaptive control
- control strategies
- control strategy
- optimal policy
- supervised learning
- temporal difference learning
- reinforcement learning methods
- least squares
- multi agent