Advancing Air Combat Tactics with Improved Neural Fictitious Self-play Reinforcement Learning.
Shaoqin HeYang GaoBaofeng ZhangHui ChangXinchen ZhangPublished in: ICIC (5) (2023)
Keyphrases
- reinforcement learning
- air combat
- fitted q iteration
- neural network
- function approximation
- network architecture
- optimal policy
- machine learning
- database
- bio inspired
- improved algorithm
- learning problems
- autonomous learning
- sensory inputs
- temporal difference
- optimal control
- transfer learning
- artificial neural networks
- multi agent
- e learning
- real time