Visual Navigation with Actor-Critic Deep Reinforcement Learning.
Kun ShaoDongbin ZhaoYuanheng ZhuQichao ZhangPublished in: IJCNN (2018)
Keyphrases
- actor critic
- visual navigation
- reinforcement learning
- temporal difference
- collision avoidance
- reinforcement learning algorithms
- policy gradient
- optimal control
- approximate dynamic programming
- neuro fuzzy
- gradient method
- function approximation
- visual odometry
- obstacle avoidance
- policy iteration
- state space
- model free
- evaluation function
- markov decision processes
- dynamic programming
- step size
- autonomous vehicles
- average reward
- mobile robot
- optimal policy
- reinforcement learning methods
- dynamic environments
- learning algorithm
- machine learning
- search algorithm
- rl algorithms
- temporal difference learning
- path planning
- learning problems
- action selection