Gym Tutorial: The Frozen Lake

In this article, we are going to learn how to create and explore the Frozen Lake environment using the Gym library, an open source project created by OpenAI used for reinforcement learning experiments. The Gym library defines a uniform interface for environments what makes the integration between algorithms and environment easier for developers. Among many ready-to-use environments, the default installation includes a text-mode version of the Frozen Lake game, used as example in our last post.

Continue reading “Gym Tutorial: The Frozen Lake”

Introduction to Reinforcement Learning: the Frozen Lake Example

Let’s understand how Reinforcement Learning works through a simple example. Let’s play a game called The Frozen Lake. Suppose you were playing frisbee with your friends in a park during winter. One of you threw the frisbee so far that it has dropped in a frozen lake. Your mission is to walk over the frozen lake to get the frisbee back, but taking caution to not fall in a hole of freezing water.

Continue reading “Introduction to Reinforcement Learning: the Frozen Lake Example”

How AI Learns to Play Games

Over the past few years, we’ve seen computer programs winning games which we believe humans were unbeatable. This belief held considering this games had so many possible moves for a given position that would be impossible to computer programs calculate all of then and choose the best ones. However, in 1997 the world witnessed what otherwise was considered impossible: the IBM Deep Blue supercomputer won a six game chess match against Gary Kasparov, the world champion of that time, by 3.5 – 2.5. Such victory would only be achieved again when DeepMind’s AlphaGo won a five game Go match against Lee Sedol, 18 times world champion, by a 4-1 score.

Continue reading “How AI Learns to Play Games”

Top 5 Free Courses in Reinforcement Learning

Reinforcement learning is not a trivial topic and even from a more practical perspective, mastering the subject requires some background in computer programming, math and probabilities. Although there’s a increasing number of libraries which offers environments and algorithms out-of-the-box, a ground base on reinforcement learning theory is essential to choose the appropriate algorithms for each kind of problem and to tune their hyperparameters when it’s necessary.

Continue reading “Top 5 Free Courses in Reinforcement Learning”