Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method.

Yang Lyu Quan Pan Jinwen Hu Chunhui Zhao Shuai Liu

Published in: CoRR (2018)

Keyphrases

gradient method
policy gradient
control policy
actor critic
convergence rate
step size
transport systems
optimization methods
convex formulation
image segmentation
optimal policy
clustering algorithm
reinforcement learning
cost function
optimization method