Skip to main content
. 2022 Mar 8;22(6):2099. doi: 10.3390/s22062099
USV unmanned surface vehicle
RL reinforcement learning
MDP Markovian decision process
DOF degree of freedom
COLREGs international regulations for preventing collisions at sea
RLCA reinforcement learning collision avoidance
D3QN dueling double-deep Q network
DQN deep Q network