Labeling Q-learning embedded with knowledge update in partially observable mdp environments

In POMDP environments, a learning agent cannot observe the environment directly, thus partially observed states appeared. In order to overcome this partially observable problem, we had proposed a new RL aJgorithm, called "Labeling Q-learning". Unlike the original LQ-learning, for an advanced LQ-Iearning, a prior knowledge about environment is prepared ahead of learning process. The knowledge is a kind of seU.organizing classification of sequences (i.e. pattern of state transition). It provides the classified sequence which consist with passed states, here it is called "group". A new LQ-learning agent assumes the transition of groups to be a landmark-like labeling situation. In this paper, we try to extend the advanced LQ-learning based on knowledge update in more extended environment. In order to demonstrate LQ-learning emhedded with knowledge which is even though made from another environment, we can apply it to Grid-World problems shown in many literatures [1].