For our first task, we will use the tic-tac-toe dataset from the ReinforcementLearning package. In this case, the dataset is built for us; however, we will investigate how it is made to understand how to get data into the proper format for reinforcement learning:
- First, let's load the tic-tac-toe data. To load the dataset, we first load the ReinforcementLearning library and then call the data function with "tictactoe" as the argument. We load our data by running the following code:
After running these lines, you will see the data object in the data Environment pane. Its current type is <Promise>; however, we will change that in the next step to see what is contained ...