End-to-end sensorimotor control problems of AUVs with deep reinforcement learning.
Hui WuShiji SongYachu HsuKeyou YouCheng WuPublished in: IROS (2019)
Keyphrases
- end to end
- control problems
- reinforcement learning
- autonomous underwater vehicle
- autonomous underwater vehicles
- optimal control
- adaptive control
- state space
- congestion control
- path planning
- multipath
- multi agent
- dynamic programming
- ad hoc networks
- learning algorithm
- continuous state spaces
- machine learning
- optimal policy
- model free
- neural network
- dead reckoning