Design of Safe Optimal Guidance With Obstacle Avoidance Using Control Barrier Function-Based Actor-Critic Reinforcement Learning.
Chi PengXiaoma LiuJianjun MaPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2023)
Keyphrases
- optimal control
- reinforcement learning
- actor critic
- obstacle avoidance
- control policy
- policy gradient
- control problems
- mobile robot
- dynamic programming
- approximate dynamic programming
- average reward
- genetic algorithm
- reinforcement learning algorithms
- temporal difference
- adaptive control
- function approximation
- path planning
- infinite horizon
- optimal policy
- action selection
- multi agent
- step size