Reinforcement learning (RL) is a new propitious research space that is well-known nowadays on the internet of things (IoT), media and social sensing computing are addressing a broad and pertinent task through making decisions sequentially by deterministic and stochastic evolutions. The IoTs extend world connectivity to physical devices like electronic devices network by use interconnect with others over the Internet with the possibility of remotely being supervised and meticulous. In this paper, we comprehensively survey an in-depth assessment of RL techniques in IoT systems focusing on the main known RL techniques like artificial neural network (ANN), Q-learning, Markov Decision Process (MDP), Learning Automata (LA). This study examines and analyses learning technique with focusing on challenges, models performance, similarities and the differences in IoTs accomplish with most correlated proposed state of the art models. The results obtained can be used as a foundation for designing, a model implementation based on the bottlenecks currently assessed with an evaluation of the most fashionable hands-on utility of current methods for reinforcement learning.