Air combat maneuver decision based on deep reinforcement learning with auxiliary reward.
Tingyu ZhangYongshuai WangMingwei SunZengqiang ChenPublished in: Neural Comput. Appl. (2024)
Keyphrases
- reinforcement learning
- air combat
- state space
- function approximation
- decision makers
- reinforcement learning algorithms
- closed loop
- decision making
- model free
- markov decision processes
- eligibility traces
- reward function
- temporal difference
- decision problems
- decision processes
- decision model
- dynamic programming
- learning algorithm
- optimal policy
- decision rules
- partially observable environments
- machine learning
- total reward
- markov decision process
- partially observable
- learning capabilities
- learning problems
- single agent
- policy iteration
- neural network
- reinforcement learning methods
- inverse reinforcement learning
- decision process
- optimal control
- robotic control
- supervised learning