Iterative reward shaping for non-overshooting altitude control of a wing-in-ground craft based on deep reinforcement learning.
Huan HuGuiyong ZhangLichao DingKuikui JiaoZhifan ZhangJi ZhangPublished in: Robotics Auton. Syst. (2023)
Keyphrases
- reward shaping
- reinforcement learning
- optimal control
- reinforcement learning algorithms
- complex domains
- function approximation
- state space
- control system
- markov decision problems
- model free
- control policy
- dynamic programming
- markov decision processes
- action selection
- policy search
- temporal difference
- neural network