Deep Reinforcement Learning-based UAV Navigation and Control: A Soft Actor-Critic with Hindsight Experience Replay Approach.
Myoung-Hoon LeeJun MoonPublished in: CoRR (2021)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- control problems
- temporal difference
- action selection
- function approximation
- approximate dynamic programming
- policy gradient
- reinforcement learning algorithms
- neuro fuzzy
- gradient method
- policy iteration
- control strategy
- control policy
- dynamic programming
- adaptive control
- markov decision processes
- control strategies
- infinite horizon
- state space
- temporal difference learning
- control method
- linear programming
- path planning
- control system
- learning algorithm
- markov decision process
- neural network
- policy gradient methods
- rl algorithms
- model free
- evaluation function
- optimal policy
- least squares
- cost function
- machine learning