A composite learning method for multi-ship collision avoidance based on reinforcement learning and inverse control.
Shuo XieXiumin ChuMao ZhengChenguang LiuPublished in: Neurocomputing (2020)
Keyphrases
- reinforcement learning
- robot control
- model free
- learning scheme
- support vector machine svm
- dynamic programming
- mathematical model
- function approximators
- collision avoidance
- theoretical analysis
- decision making
- learning algorithm
- input output
- learning tasks
- inductive learning
- relational learning
- control system
- evolutionary algorithm
- search space