On improving the properties of random walk on graph using Q-learning

Studies have recently been conducted to model mobile agents on unknown graphs, such as random walks (RWs) and understand their mathematical properties. In this study, we investigate the extent which properties of RWs can be improved when access very limited information. We propose Q-weighted walk (QW-RW), in an agent decides a next node by using Q-values learned Q-learning, examine its effectiveness. find that small scale-free QW-RW is 1.25 times faster than self-avoiding RW cover 80% entire graph.