Hybrid Policy Learning for Multi-Agent Pathfinding.

Alexey Skrynnik Alexandra Yakovleva Vasilii Davydov Konstantin S. Yakovlev Aleksandr I. Panov

Published in: IEEE Access (2021)

Keyphrases

multi agent
learning algorithm
learning tasks
concept learning
path finding
learning problems
prior knowledge
knowledge acquisition
path planning
learning scheme
machine learning
reinforcement learning
search algorithm
semi supervised
optimal policy
inductive learning