Training Drift Counteraction Optimal Control Policies Using Reinforcement Learning: An Adaptive Cruise Control Example.
Zhaojian LiTianshu ChuIlya V. KolmanovskyXiang YinPublished in: IEEE Trans. Intell. Transp. Syst. (2018)
Keyphrases
- control policies
- reinforcement learning
- control policy
- optimal policy
- continuous state
- stochastic optimization problems
- action space
- control strategies
- control system
- motion control
- long run
- state space
- supervised learning
- finite horizon
- optimal control
- learning algorithm
- average cost
- markov decision processes
- infinite horizon
- finite state
- reward function
- action selection
- neural network
- decision problems
- multistage
- sufficient conditions
- dynamic programming
- genetic algorithm