Abstract
Chain Form Reinforcement Learning (CFRL) was proposed for a reinforcement learning agent using low memory. In this paper, we introduce Sneak Form Reinforcement Learning (SFRL). SFRL is the method which we improve CFRL in terms of Contextual Learning. If a sequence of state-action pairs has a shortest path, a SFRL agent cuts and saves the path. To improve the performance of SFRL, we introduce Majority Vote of Neighborhood Conditions (MVNC) for SFRL. MVNC is the rule which agent in an unknown condition selects an action not at random but with circumjacent information. Our method was made a comparison between Q-Learning and CFRL in several easy simulations. We examined performance and discussed the best usage environment.
