Policy Iteration Based Approximate Dynamic Programming Toward Autonomous Driving in Constrained Dynamic Environment.
Ziyu LinJun MaJingliang DuanShengbo Eben LiHaitong MaBo ChengTong Heng LeePublished in: IEEE Trans. Intell. Transp. Syst. (2023)
Keyphrases
- dynamic environments
- approximate dynamic programming
- policy iteration
- autonomous driving
- markov decision processes
- grand challenge
- reinforcement learning
- model free
- optimal policy
- stereo vision
- fixed point
- least squares
- temporal difference
- factored mdps
- linear program
- mobile robot
- finite state
- dynamic programming
- markov decision process
- path planning
- markov decision problems
- infinite horizon
- average cost
- convergence rate
- optimal control
- linear programming
- state space
- reinforcement learning algorithms
- evaluation function
- monte carlo
- evolutionary algorithm