A proposition of adaptive state space partition in reinforcement learning with Voronoi Tessellation

This paper presents a new adaptive segmentation of continuous state space based on vector quantization algorithm such as LBG (Linde-Buzo-Gray) for high-dimensional continuous state spaces. The objective of adaptive state space partitioning is to develop the efficiency of learning reward values with an accumulation of state transition vector (STV) in a single-agent environment. We constructed our single-agent model in continuous state and discrete actions spaces using Q-learning function. Moreover, the study of the resulting state space partition reveals in a Voronoi tessellation. In addition, the experimental results show that this proposed method can partition the continuous state space appropriately into Voronoi regions according to not only the number of actions, and achieve a good performance of reward based learning tasks compared with other approaches such as square partition lattice.