Learn How AI Mastered the Game of "Go" in 24 Hours
The game of “Go” is more complex than chess, which makes it a perfect candidate for testing AI’s ability to learn. The research team and AI-developers at DeepMind developed AI known as AlphaGo, to learn how to master the game. It was trained on a database of human Go games, such that its strategies were based on what it could learn from human iterations of the game. AlphaGo was able to defeat world champion Go player Lee Sedol in 2016.
Since that time, the AI has gotten even better at the game. In the latest iteration of AlphaGo, known as AlphaGo Zero, the AI learned to play the ancient game without feedback from humans or data on their past play. Instead, the new AlphaGo Zero started with just knowledge of the rules and learned from the success of a million random moves it made against itself. AlphaGo Zero's artificial neural networks use the current state of the game as input, and through trial and error and feedback in the form of winning, the AI learned how to play. This reinforcement learning strategy, which was used extensively by AlphaGo as well, has its roots in psychology: the neural network learns from rewards like humans do.
The results? After just three days of training, the the AlphaGo Zero AI beat the original AlphaGo 100 to 0 — and was also able to create new moves in the process!
The DeepMind researchers wrote: "the self-learned player (AlphaGo Zero) performed much better overall, defeating the human-trained player within the first 24 hours of training. This suggests that AlphaGo Zero may be learning a strategy that is qualitatively different to human play.”
The point of this story is that AI is getting stronger and faster by the day, and its ability to solve complex problems will no doubt make it invaluable to corporations and even individuals. As I’ve written before, when it comes to the investment world, hedge funds and big Wall St. firms are already using AI in their sophisticated quant strategies, and in many cases the AI is making trades and finding patterns. You can too. Tickeron’s AI is available to retail investors and can be used to find patterns, trends, and to generate trading ideas. These high-powered algorithms are finding new ideas every day, and can be delivered right to your inbox.
Contributor
Sergey Savastiouk, Ph.D. has a degree in Applied Mathematics from Moscow University and has extensive experience as an entrepreneur, investor, manager, and mathematician. His professional expertise is in applied mathematics, mathematical modeling, system and pattern analysis, and software and hardware system integration. He has served as the CEO of several hi-tech start-up companies and nonprofit organizations, which has given him proven capabilities in business strategy for high-tech start-up companies, market assessment, company formation, team building, product development, marketing, and sales. He has published numerous articles in journals and magazines on related fields. As a retail investor, he spent 15 years developing his proprietary trading and quantitative algorithms (now Tickeron’s A.I.), which brought him significant returns in trading the stock market. His current work and goal in founding Tickeron is to bring professional, sophisticated stock market analysis capabilities to retail investors via an easy-to-use interface.
Advertisement