01. Fundamentals of Reinforcement Learning/1.12. Applications of Reinforcement Learning.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Applications of Reinforcement Learning\n",
    "\n",
    "Reinforcement learning has evolved rapidly over the past couple of years with a wide range of applications ranging from playing games to self-driving cars. One of the major reasons for this evolution is due to deep reinforcement learning (DRL) which is a combination of reinforcement learning and deep learning. We will learn about the various state of the art deep reinforcement learning algorithms in the upcoming chapters so be excited. In this section, we will look into some of the real-life applications of reinforcement learning.\n",
    "\n",
    "__Manufacturing__ - In manufacturing, intelligent robots are trained using reinforcement learning to place objects in the right position. The use of intelligent robots reduces labor costs and increases productivity. \n",
    "\n",
    "Dynamic Pricing - One of the popular applications of reinforcement learning includes dynamic pricing. Dynamic pricing implies that we change the price of the products based on demand and supply. We can train the RL agent for the dynamic pricing of the products with the goal of maximizing the revenue.\n",
    "\n",
    "__Inventory management__ - Reinforcement learning is extensively used in inventory management which is a crucial business activity. Some of these activities include supply chain management, demand forecasting, and handling several warehouse operations (such as placing products in warehouses for managing space efficiently).\n",
    "\n",
    "__Recommendation System__ - Reinforcement learning is widely used in building a recommendation system where the behavior of the user constantly changes. For instance, in the music recommendation system, the behavior or the music preference of the user changes from time to time. So in those cases using an RL agent can be very useful as the agent constantly learn by interacting with the environment. \n",
    "\n",
    "__Neural Architecture search__ - In order for the neural networks to perform a given task with good accuracy, the architecture of the network is very important and it has to properly designed. With reinforcement learning, we can automate the process of complex neural architecture search by training the agent to find the best neural architecture for a given task with the goal of maximizing the accuracy.\n",
    "\n",
    "__Natural Language Processing__ - With the increase in popularity of the deep reinforcement algorithms, RL has been widely used in several NLP tasks such as abstractive text summarization, chatbots and more.\n",
    "\n",
    "__Finance__ - Reinforcement learning is widely used in financial portfolio management which is the process of constant redistribution of a fund into different financial products. RL is also used in predicting and trading in commercial transaction markets. JP Morgan has successfully used RL to provide better trade execution results for large orders."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}