A Dynamics and Task Decoupled Reinforcement Learning Architecture for High-Efficiency Dynamic Target Intercept.
Dora D. LiuLiang HuQi ZhangTangwei YeUsman NaseemZhong Yuan LaiPublished in: AAAI (2023)
Keyphrases
- high efficiency
- reinforcement learning
- high accuracy
- real and synthetic datasets
- density based clustering
- dynamical systems
- dynamic environments
- result quality
- memory space
- real time
- state space
- learning process
- dynamic model
- machine learning
- multi layer
- network architecture
- learning capabilities
- software architecture
- arbitrary shape
- target object
- optimal policy
- learning algorithm
- neural network