Multi-policy Soft Actor-Critic Reinforcement Learning for Autonomous Racing.
Feifan TongRan LiuGuodong YinSunan ZhangWeichao ZhuangPublished in: AMC (2024)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- approximate dynamic programming
- optimal control
- reinforcement learning algorithms
- gradient method
- neuro fuzzy
- policy iteration
- function approximation
- policy gradient methods
- model free
- rl algorithms
- action selection
- control problems
- optimal policy
- state space
- step size
- evaluation function
- adaptive control
- learning capabilities
- multi agent
- average reward
- learning algorithm
- supervised learning
- temporal difference learning
- linear program
- partially observable markov decision processes