April 2018
Intermediate to advanced
334 pages
10h 18m
English
Here, we will try to implement the object detection problem in terms of a reinforcement learning framework where a reinforcement learning agent will interact with the image of the environment and with every time step the agent will decide which region to focus attention on with the goal of finding the object in minimal time steps. The problem statement is represented as a Markov Decision Processes (MDP) framework and its different parameters are discussed as follows: