ETRI ETRI This document describes agent reinforcement learning (RL) in a distributed environment to transfer or share information for autonomous shortest path-planning over a communication network. The centralized node, which is the main node to manage agent workflow in hybrid peer-to-peer environment, provides a cumulative reward for each action that a given agent takes with respect to an optimal path based on a to-be-learned policy over the learning process. A reward from the centralized node is reflected when an agent explores to reach its destination for autonomous shortest path-planning in distributed nodes.