Multi-Objective End-to-End Self-Driving Based on Pareto-Optimal Actor-Critic Approach.
Tinghan WangYugong LuoJinxin LiuKeqiang LiPublished in: ITSC (2021)
Keyphrases
- end to end
- pareto optimal
- multi objective
- actor critic
- reinforcement learning
- multi objective optimization
- nsga ii
- evolutionary algorithm
- policy gradient
- optimal control
- temporal difference
- approximate dynamic programming
- neuro fuzzy
- optimization algorithm
- multiple objectives
- gradient method
- reinforcement learning algorithms
- particle swarm optimization
- conflicting objectives
- function approximation
- pareto optimal set
- objective function
- genetic algorithm
- average reward
- policy iteration
- multi objective optimization problems
- bi objective
- markov decision processes
- multi objective evolutionary algorithms
- pareto optimal solutions
- optimization problems
- real time
- step size
- dynamic programming
- evaluation function
- convergence rate