A Model-free Deep Reinforcement Learning Approach To Maneuver A Quadrotor Despite Single Rotor Failure.
Paras SharmaPrithvi PoddarP. B. SujitPublished in: CoRR (2021)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy iteration
- learning algorithm
- rl algorithms
- neural network
- reinforcement learning methods
- machine learning
- impedance control
- markov decision processes
- supervised learning
- learning process
- mathematical model
- k nearest neighbor
- learning problems
- closed loop
- knn
- state space
- dynamic programming
- function approximators
- multi agent
- training data
- genetic algorithm