# Motivation behind RL

```{figure} Images/motivation.png
---
width: 85%
align: center
name: motivation
---
Phases of Industrial Revolution
```

<b>Industrial Revolution</b> has played a pivotal role in the development of technology and services. In simplest sense, it can be defined as <strong><em>automation of repeated physical solutions</em></strong>.

It has paved way into <strong><em>automation of repeated mental solutions</em></strong>, forming the focus of <b>Digital revolution</b>, which led into the <b>Information age</b>.

```{figure} Images/robot_think.jpg
---
width: 40%
align: center
name: motivation
---
Next Step: Allow machines to find solutions themselves
```

<b>Reinforcement Learning</b> is one of the pieces of the puzzle that fits into the next step, i.e., <strong><em>learning autonomously how to make decisions</em></strong>. Under this, we can point out at least two distinct reasons to learn,
<ol>
    <li> <b>Finding previously unknown solutions</b>
    <br>
    For example,
    <ul>
        <li> Achieving human level performance in atari games
        <li> Finding shortest or optimal paths in a network or maze
        <li> Finding optimal decision making strategy for any custom system with very high dimensional spaces
    </ul>
    <li> <b>Finding solutions online during operation</b>
    <br>
    For example,
    <ul>
        <li> robot learning to navigate terrains which greatly differ from expectations
        <li> A cleaning bot learning the best strategy to clean any room or house that it is placed into
        <li> Learning optimal control decisions like increasing or decreasing temperature for an automatic thermostat
    </ul>
</ol>