Entropy and PCA Analysis for Environments Associated to Q-Learning for Path Finding
Manuel Garcia-Quijada, Efrén Gorrostieta-Hurtado, José Emilio Vargas-Soto, Manuel Toledano‐Ayala · 2019
This work is based on the simulation of the reinforcement learning method for path search for mobile robotic agents in unstructured environments. Likewise, a performance metric of the Q-learning algorithm is proposed, based on the Entropy and Principal Component Analysis of the environment representative images. The advantage of this analysis is that could be estimated the level of complexity as a function of environment randomness.