Summary

We started the chapter by understanding the basic idea of RL. We learned that RL is a trial and error learning process and the learning in RL happens based on a reward. We then explored the difference between RL and the other ML paradigms, such as supervised and unsupervised learning. Going ahead, we learned about the MDP and how the RL environment can be modeled as an MDP. Next, we understood several important fundamental concepts involved in RL, and at the end of the chapter we looked into some real-life applications of RL.

Thus, in this chapter, we have learned several fundamental concepts of RL. In the next chapter, we will begin our Hands-on reinforcement learning journey by implementing all the fundamental concepts we have learned in this chapter using the popular toolkit called Gym.