In this chapter, we understood what reinforcement learning is and how it stands out from other machine learning algorithms. The components of reinforcement learning were individually explained and we enhanced our understanding through examples. Then, reinforcement learning algorithms were introduced, both practically and mathematically, using suitable examples. We also saw reinforcement learning implementations in ROS, where robots such as TurtleBot 2 and the MARA robot arm were used in application-specific environments, and we understood how they're implemented and their usage. This chapter acted as a simple and gentle introduction to machine learning and its usage in ROS.
In the next chapter, we will see how deep we can dive into machine learning methods to make the agent more effective in terms of learning and achieving its goal.
