Centralized Patrolling With Weakly-Coupled Agents Using Monte Carlo Tree Search.

Xin Zhou Weiping Wang Yifan Zhu Tao Wang Bo Zhang

Published in: IEEE Access (2019)

Keyphrases

monte carlo tree search
multi agent
monte carlo
multi agent systems
single agent
tree search algorithm
multiple agents
evaluation function
bayesian reinforcement learning
dynamic environments
action selection
temporal difference
decision making
upper bound
learning tasks
temporal difference learning