Reinforcement Learning with Safe Action Generation for Autonomous Racing.
Jiacheng YangYuanda WangLu DongXin YuanPublished in: CEC (2024)
Keyphrases
- reinforcement learning
- autonomous learning
- action selection
- partially observable domains
- function approximation
- learning capabilities
- reward shaping
- action space
- cooperative
- learning algorithm
- multi agent
- learning process
- dynamic programming
- model free
- data sets
- robotic control
- neural network
- fitted q iteration
- transition model
- temporal difference learning
- autonomous systems
- autonomous navigation
- generation process
- temporal difference
- robotic systems
- genetic algorithm