Safe Reinforcement Learning for Autonomous Vehicle Using Monte Carlo Tree Search.
Shuojie MoXiaofei PeiChaoxian WuPublished in: IEEE Trans. Intell. Transp. Syst. (2022)
Keyphrases
- monte carlo tree search
- autonomous vehicles
- reinforcement learning
- temporal difference
- reinforcement learning methods
- bayesian reinforcement learning
- robot control
- monte carlo
- temporal difference learning
- path planning
- evaluation function
- obstacle avoidance
- function approximation
- reinforcement learning algorithms
- model free
- mobile robot
- multiagent systems
- state space
- learning algorithm
- multi agent
- autonomous agents
- function approximators
- control problems
- markov chain
- input output
- autonomous robots
- control strategies
- dynamic environments
- motion planning
- particle filter
- supervised learning
- action space
- optimal control
- real time
- optimal policy
- markov decision processes