A Beginner’s Guide to Deep Reinforcement Learning
The game of Go has simple rules but complex play. Each turn, a player has something in the vicinity of 2 x 10170 board positions to consider. Experienced players learn what is likely to work by trial and error over years of play in a process known as reinforcement learning.
So what do you get when you give artificial intelligence (AI) the data from thousands of games between professional Go players? AI that beats the top-ranked human Go player – AlphaGo. That is deep learning in action.
But what if instead you teach AI the rules of Go and let it play millions of games between itself? Deep reinforcement learning enables AI to teach itself by creating its own data (the millions of games) and analyzing the moves to arrive at the best one. Like a learning human, AI adjusts its responses according to failure or success to improve the outcome. It just does it at a scale and speed well beyond human capability.
Deep reinforcement learning needs to work inside a structure. This takes into account the context of the environment – whether that is the rules of Go, or the market in the case of your campaign – before you set a goal. An AI with deep reinforcement learning will then be able to help you with your strategy and actions based on the lessons learnt not only from previous campaigns, but also from the scenarios it has played out in its own internal iterations to give you an understanding of what is likely to happen.
It will also continue to learn as you roll your campaigns out, figuring out not just what works and what doesn’t but analyzing factors such as profitability, so you can optimize future campaigns by lowering your cost per lead, for example, or by targeting users who are likely to spend more.
Consider a campaign in which you want to maximize the number of app installations. You have a budget, so the aim is to obtain the highest number of installations for the amount you have (goal). You need to figure out where to allocate your budget and what to set as the bid price (actions). Using the deep reinforcement learning technique, AI will suggest a strategy based on its understanding of budgets and prices to find the best platforms and timing. It will suggest actions for you so you can leverage the most advantageous opportunities. And if the environment changes, it will learn what works and what doesn’t much quicker than a human marketer.
Deep reinforcement learning is ideal for complex environments where there are several alternative paths, such as marketing where you are dealing with human behavior. Its most valuable advantage is that it learns from mistakes in order to optimize quickly.
WE ARE HERE TO HELP
YOU MIGHT ALSO LIKE
Author | Min Sun, Chief AI Scientist, Appier We are at a very exciting juncture in the development of artificial intelligence (AI), starting to see implementations of the third wave of the technology – this involves machines far surpassing human capabilities in various application domains, and that creates all kinds of opportunities for businesses. To leverage this to its full potential, companies need to rethink how they operate and put AI at the heart of everything they do. Making Waves: How AI Is Changing the Way We Do Business The first AI wave started with statistics-based systems – the best-known use would probably be information retrieval algorithms used by big internet companies like Google in the early years of AI (thinking of the PageRank search engine). The second wave was about many more machine learning techniques, like logistic regressions, supporting vector machines, and so on. This is used in all kinds of businesses like banking and digital marketing tools. The third wave is deep learning, of which the use is manifest in so-called perception AI – this relates to our human perception system including sight, hearing, touch and so on. Think of speech recognition and image recognition. It’s used
Exit-intent technology is a highly-underused tool. However, when implemented effectively, it can encourage visitors who would have otherwise abandoned your site to stay and even to convert. So, what is exit-intent technology? When should you use it? How to make it work for your brand? Read on. What Is Exit-Intent Technology? Exit-intent technology is smart behavioral software that tracks online visitors’ mouse movements on a webpage. The purpose of exit-intent technology is to help marketers detect when a visitor is going to leave a site without making a purchase. Every exit-intent provider uses different algorithms and technology and responds to different types of visitor mouse activity. Movements that indicate abandonment include when the cursor moves towards the back button, remains idle, or scrolls up quickly. When signs of abandonment or customer intent such as these are identified, exit-intent technology automatically delivers a pop-up message that engages visitors with an enticing offer, product recommendation, or other messages to encourage them to stay and convert. When Should Marketers Use Exit-intent Technology? Exit-intent technology works well on e-commerce websites, landing pages, and commercial websites. Marketers should use exit-intent technology if they are looking to capture more potential customers, reduce cart adornment,
The last few years has seen artificial intelligence (AI) go from a promising buzzword to a mainstream technology. Almost every industry from banking to telecoms, healthcare and insurance is experimenting with some form of AI, and the retail industry is no exception. Based on a recent study, the investment in AI in the retail market is estimated to be US$27.2 billion by 2025, almost 38 times US$0.71 billion – the value in 2016. This leap is understandable considering the shifts in consumers’ shopping habits and fervent activity in the sector, as well as the number of ways in which AI can impact and transform the industry. AI is Disrupting the Entire Retail Chain Compared to other industries like financial services and insurance, the retail sector is further ahead in the implementation of AI. A new survey conducted by Forrester on behalf of Appier shows that 56 percent of respondents from the retail sector in Asia Pacific (APAC) have either implemented, or are expanding their AI-oriented initiatives. The adoption of AI can be seen right at the beginning, in the manufacturing stage. Brands like Adidas and Nike employ robots powered by AI and computer vision to automate tasks that would