In this, level sets the information a RL agent gets from the environment. The car
is 2 × 2 pixels, and cannot leave the field. The track segments are 6 pixels wide, and
have positions from 1 (left) to 5 (right), and the car has 7 different positions . The front of the car must remain on
drivable terrain at all times. The rear of the car is allowed to come off road with no penalty.
At each step during a race, the agent will get a reward of +1. Once the front of the car
comes off road, the episode finishes.
Task 1: Train a CNN to predict a clear road ahead 15 points
The python program sprites.py creates a training and test set of “minirace” scenes,
trainingpix.csv and testingpix.csv . Each
row represents a 16 × 16 screenshot , plus an extra value
of either 0 or 1 that indicates if the car can safely drive straight without going off-road
in the immediate next step.
Steps
1. Create the datasets by running the sprites.py code.
2. Create a CNN that predicts the whether the car can safely remain on the current
position without crashing into non-drivable terrain.
(a) Describe : what is a good loss function for this problem?
(b) Implement and train the CNN on the training set.
(c) Compute the accuracy of your model on the test data set.
• Your are free to choose the architecture of your network, but there should be
at least one convolutional layer.
• You can normalise/standardise the data if it helps improve the training.
What to submit:
• A description of your CNN and the training. Calculate the size of each layer,
and include it in the description.
• Include the explanation for the loss function in your description.
• For how long did you train your model ? What is the performance on the test set?
• Submit the python code for your solution .
