Reinforcement learning with raw image pixels as state input

Ernst, Damien , Raphael Marée, Louis Wehenkel
Reinforcement learning with raw image pixels as state input
International Workshop on Intelligent Computing in Pattern Analysis/Synthesis (IWICPAS). Proceedings series: Lecture Notes in Computer Science, Volume 4153, page 446-454, August 2006

Abstract: We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to carry out the simulation is a batch-mode algorithm known as fitted Q iteration.